diff options
| author | Ingo Molnar <mingo@kernel.org> | 2016-03-21 10:47:40 +0100 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2016-03-21 10:47:40 +0100 |
| commit | 42e405f7b1d252c90a2468dd2140f47b8142b7a0 (patch) | |
| tree | baeda52d8726fe694d3344a0d0fda1dadc30a901 /kernel | |
| parent | e9532e69b8d1d1284e8ecf8d2586de34aec61244 (diff) | |
| parent | 710d60cbf1b312a8075a2158cbfbbd9c66132dcc (diff) | |
| download | op-kernel-dev-42e405f7b1d252c90a2468dd2140f47b8142b7a0.zip op-kernel-dev-42e405f7b1d252c90a2468dd2140f47b8142b7a0.tar.gz | |
Merge branch 'linus' into sched/urgent, to pick up dependencies
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel')
62 files changed, 3518 insertions, 1360 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index 5b9d396..6ea42e8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -22,13 +22,88 @@ #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> +#include <linux/smpboot.h> + #include <trace/events/power.h> +#define CREATE_TRACE_POINTS +#include <trace/events/cpuhp.h> #include "smpboot.h" +/** + * cpuhp_cpu_state - Per cpu hotplug state storage + * @state: The current cpu state + * @target: The target state + * @thread: Pointer to the hotplug thread + * @should_run: Thread should execute + * @cb_stat: The state for a single callback (install/uninstall) + * @cb: Single callback function (install/uninstall) + * @result: Result of the operation + * @done: Signal completion to the issuer of the task + */ +struct cpuhp_cpu_state { + enum cpuhp_state state; + enum cpuhp_state target; +#ifdef CONFIG_SMP + struct task_struct *thread; + bool should_run; + enum cpuhp_state cb_state; + int (*cb)(unsigned int cpu); + int result; + struct completion done; +#endif +}; + +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); + +/** + * cpuhp_step - Hotplug state machine step + * @name: Name of the step + * @startup: Startup function of the step + * @teardown: Teardown function of the step + * @skip_onerr: Do not invoke the functions on error rollback + * Will go away once the notifiers are gone + * @cant_stop: Bringup/teardown can't be stopped at this step + */ +struct cpuhp_step { + const char *name; + int (*startup)(unsigned int cpu); + int (*teardown)(unsigned int cpu); + bool skip_onerr; + bool cant_stop; +}; + +static DEFINE_MUTEX(cpuhp_state_mutex); +static struct cpuhp_step cpuhp_bp_states[]; +static struct cpuhp_step cpuhp_ap_states[]; + +/** + * cpuhp_invoke_callback _ Invoke the callbacks for a given state + * @cpu: The cpu for which the callback should be invoked + * @step: The step in the state machine + * @cb: The callback function to invoke + * + * Called from cpu hotplug and from the state register machinery + */ +static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step, + int (*cb)(unsigned int)) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret = 0; + + if (cb) { + trace_cpuhp_enter(cpu, st->target, step, cb); + ret = cb(cpu); + trace_cpuhp_exit(cpu, st->state, step, ret); + } + return ret; +} + #ifdef CONFIG_SMP /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); +bool cpuhp_tasks_frozen; +EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when @@ -207,31 +282,281 @@ int __register_cpu_notifier(struct notifier_block *nb) return raw_notifier_chain_register(&cpu_chain, nb); } -static int __cpu_notify(unsigned long val, void *v, int nr_to_call, +static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call, int *nr_calls) { + unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0; + void *hcpu = (void *)(long)cpu; + int ret; - ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call, + ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call, nr_calls); return notifier_to_errno(ret); } -static int cpu_notify(unsigned long val, void *v) +static int cpu_notify(unsigned long val, unsigned int cpu) { - return __cpu_notify(val, v, -1, NULL); + return __cpu_notify(val, cpu, -1, NULL); } -#ifdef CONFIG_HOTPLUG_CPU +/* Notifier wrappers for transitioning to state machine */ +static int notify_prepare(unsigned int cpu) +{ + int nr_calls = 0; + int ret; + + ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls); + if (ret) { + nr_calls--; + printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n", + __func__, cpu); + __cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL); + } + return ret; +} + +static int notify_online(unsigned int cpu) +{ + cpu_notify(CPU_ONLINE, cpu); + return 0; +} + +static int notify_starting(unsigned int cpu) +{ + cpu_notify(CPU_STARTING, cpu); + return 0; +} + +static int bringup_wait_for_ap(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + wait_for_completion(&st->done); + return st->result; +} + +static int bringup_cpu(unsigned int cpu) +{ + struct task_struct *idle = idle_thread_get(cpu); + int ret; + + /* Arch-specific enabling code. */ + ret = __cpu_up(cpu, idle); + if (ret) { + cpu_notify(CPU_UP_CANCELED, cpu); + return ret; + } + ret = bringup_wait_for_ap(cpu); + BUG_ON(!cpu_online(cpu)); + return ret; +} + +/* + * Hotplug state machine related functions + */ +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = steps + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->startup); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + struct cpuhp_step *step = steps + st->state; + + ret = cpuhp_invoke_callback(cpu, st->state, step->teardown); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st, steps); + break; + } + } + return ret; +} + +static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps) +{ + for (st->state--; st->state > st->target; st->state--) { + struct cpuhp_step *step = steps + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } +} + +static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + while (st->state < target) { + struct cpuhp_step *step; + + st->state++; + step = steps + st->state; + ret = cpuhp_invoke_callback(cpu, st->state, step->startup); + if (ret) { + st->target = prev_state; + undo_cpu_up(cpu, st, steps); + break; + } + } + return ret; +} + +/* + * The cpu hotplug threads manage the bringup and teardown of the cpus + */ +static void cpuhp_create(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + init_completion(&st->done); +} + +static int cpuhp_should_run(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + + return st->should_run; +} + +/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ +static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); + + return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target); +} + +/* Execute the online startup callbacks. Used to be CPU_ONLINE */ +static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target); +} + +/* + * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke + * callbacks when a state gets [un]installed at runtime. + */ +static void cpuhp_thread_fun(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + int ret = 0; + + /* + * Paired with the mb() in cpuhp_kick_ap_work and + * cpuhp_invoke_ap_callback, so the work set is consistent visible. + */ + smp_mb(); + if (!st->should_run) + return; + + st->should_run = false; + + /* Single callback invocation for [un]install ? */ + if (st->cb) { + if (st->cb_state < CPUHP_AP_ONLINE) { + local_irq_disable(); + ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); + local_irq_enable(); + } else { + ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); + } + } else { + /* Cannot happen .... */ + BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + + /* Regular hotplug work */ + if (st->state < st->target) + ret = cpuhp_ap_online(cpu, st); + else if (st->state > st->target) + ret = cpuhp_ap_offline(cpu, st); + } + st->result = ret; + complete(&st->done); +} -static void cpu_notify_nofail(unsigned long val, void *v) +/* Invoke a single callback on a remote cpu */ +static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, + int (*cb)(unsigned int)) { - BUG_ON(cpu_notify(val, v)); + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + if (!cpu_online(cpu)) + return 0; + + st->cb_state = state; + st->cb = cb; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_completion(&st->done); + return st->result; } + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) +{ + st->result = 0; + st->cb = NULL; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); +} + +static int cpuhp_kick_ap_work(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state state = st->state; + + trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); + __cpuhp_kick_ap_work(st); + wait_for_completion(&st->done); + trace_cpuhp_exit(cpu, st->state, state, st->result); + return st->result; +} + +static struct smp_hotplug_thread cpuhp_threads = { + .store = &cpuhp_state.thread, + .create = &cpuhp_create, + .thread_should_run = cpuhp_should_run, + .thread_fn = cpuhp_thread_fun, + .thread_comm = "cpuhp/%u", + .selfparking = true, +}; + +void __init cpuhp_threads_init(void) +{ + BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); + kthread_unpark(this_cpu_read(cpuhp_state.thread)); +} + +#ifdef CONFIG_HOTPLUG_CPU EXPORT_SYMBOL(register_cpu_notifier); EXPORT_SYMBOL(__register_cpu_notifier); - void unregister_cpu_notifier(struct notifier_block *nb) { cpu_maps_update_begin(); @@ -311,57 +636,60 @@ static inline void check_for_tasks(int dead_cpu) read_unlock(&tasklist_lock); } -struct take_cpu_down_param { - unsigned long mod; - void *hcpu; -}; +static void cpu_notify_nofail(unsigned long val, unsigned int cpu) +{ + BUG_ON(cpu_notify(val, cpu)); +} + +static int notify_down_prepare(unsigned int cpu) +{ + int err, nr_calls = 0; + + err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls); + if (err) { + nr_calls--; + __cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL); + pr_warn("%s: attempt to take down CPU %u failed\n", + __func__, cpu); + } + return err; +} + +static int notify_dying(unsigned int cpu) +{ + cpu_notify(CPU_DYING, cpu); + return 0; +} /* Take this CPU down. */ static int take_cpu_down(void *_param) { - struct take_cpu_down_param *param = _param; - int err; + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); + int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; - cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Invoke the former CPU_DYING callbacks */ + for (; st->state > target; st->state--) { + struct cpuhp_step *step = cpuhp_ap_states + st->state; + + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } /* Give up timekeeping duties */ tick_handover_do_timer(); /* Park the stopper thread */ - stop_machine_park((long)param->hcpu); + stop_machine_park(cpu); return 0; } -/* Requires cpu_add_remove_lock to be held */ -static int _cpu_down(unsigned int cpu, int tasks_frozen) +static int takedown_cpu(unsigned int cpu) { - int err, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; - struct take_cpu_down_param tcd_param = { - .mod = mod, - .hcpu = hcpu, - }; - - if (num_online_cpus() == 1) - return -EBUSY; - - if (!cpu_online(cpu)) - return -EINVAL; - - cpu_hotplug_begin(); - - err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); - if (err) { - nr_calls--; - __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); - pr_warn("%s: attempt to take down CPU %u failed\n", - __func__, cpu); - goto out_release; - } + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; /* * By now we've cleared cpu_active_mask, wait for all preempt-disabled @@ -378,6 +706,8 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) else synchronize_rcu(); + /* Park the smpboot threads */ + kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); smpboot_park_threads(cpu); /* @@ -389,12 +719,12 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* * So now all preempt/rcu users must observe !cpu_active(). */ - err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); + err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ - cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); + cpu_notify_nofail(CPU_DOWN_FAILED, cpu); irq_unlock_sparse(); - goto out_release; + return err; } BUG_ON(cpu_online(cpu)); @@ -405,10 +735,8 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) * * Wait for the stop thread to go away. */ - while (!per_cpu(cpu_dead_idle, cpu)) - cpu_relax(); - smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ - per_cpu(cpu_dead_idle, cpu) = false; + wait_for_completion(&st->done); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); @@ -417,20 +745,104 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* This actually kills the CPU. */ __cpu_die(cpu); - /* CPU is completely dead: tell everyone. Too late to complain. */ tick_cleanup_dead_cpu(cpu); - cpu_notify_nofail(CPU_DEAD | mod, hcpu); + return 0; +} +static int notify_dead(unsigned int cpu) +{ + cpu_notify_nofail(CPU_DEAD, cpu); check_for_tasks(cpu); + return 0; +} -out_release: +static void cpuhp_complete_idle_dead(void *arg) +{ + struct cpuhp_cpu_state *st = arg; + + complete(&st->done); +} + +void cpuhp_report_idle_dead(void) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + + BUG_ON(st->state != CPUHP_AP_OFFLINE); + rcu_report_dead(smp_processor_id()); + st->state = CPUHP_AP_IDLE_DEAD; + /* + * We cannot call complete after rcu_report_dead() so we delegate it + * to an online cpu. + */ + smp_call_function_single(cpumask_first(cpu_online_mask), + cpuhp_complete_idle_dead, st, 0); +} + +#else +#define notify_down_prepare NULL +#define takedown_cpu NULL +#define notify_dead NULL +#define notify_dying NULL +#endif + +#ifdef CONFIG_HOTPLUG_CPU + +/* Requires cpu_add_remove_lock to be held */ +static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, + enum cpuhp_state target) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int prev_state, ret = 0; + bool hasdied = false; + + if (num_online_cpus() == 1) + return -EBUSY; + + if (!cpu_present(cpu)) + return -EINVAL; + + cpu_hotplug_begin(); + + cpuhp_tasks_frozen = tasks_frozen; + + prev_state = st->state; + st->target = target; + /* + * If the current CPU state is in the range of the AP hotplug thread, + * then we need to kick the thread. + */ + if (st->state > CPUHP_TEARDOWN_CPU) { + ret = cpuhp_kick_ap_work(cpu); + /* + * The AP side has done the error rollback already. Just + * return the error code.. + */ + if (ret) + goto out; + + /* + * We might have stopped still in the range of the AP hotplug + * thread. Nothing to do anymore. + */ + if (st->state > CPUHP_TEARDOWN_CPU) + goto out; + } + /* + * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need + * to do the further cleanups. + */ + ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target); + + hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE; +out: cpu_hotplug_done(); - if (!err) - cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); - return err; + /* This post dead nonsense must die */ + if (!ret && hasdied) + cpu_notify_nofail(CPU_POST_DEAD, cpu); + return ret; } -int cpu_down(unsigned int cpu) +static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; @@ -441,100 +853,131 @@ int cpu_down(unsigned int cpu) goto out; } - err = _cpu_down(cpu, 0); + err = _cpu_down(cpu, 0, target); out: cpu_maps_update_done(); return err; } +int cpu_down(unsigned int cpu) +{ + return do_cpu_down(cpu, CPUHP_OFFLINE); +} EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ -/* - * Unpark per-CPU smpboot kthreads at CPU-online time. +/** + * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers + * @cpu: cpu that just started + * + * This function calls the cpu_chain notifiers with CPU_STARTING. + * It must be called by the arch code on the new cpu, before the new cpu + * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ -static int smpboot_thread_call(struct notifier_block *nfb, - unsigned long action, void *hcpu) +void notify_cpu_starting(unsigned int cpu) { - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); - case CPU_DOWN_FAILED: - case CPU_ONLINE: - smpboot_unpark_threads(cpu); - break; + while (st->state < target) { + struct cpuhp_step *step; - default: - break; + st->state++; + step = cpuhp_ap_states + st->state; + cpuhp_invoke_callback(cpu, st->state, step->startup); } - - return NOTIFY_OK; } -static struct notifier_block smpboot_thread_notifier = { - .notifier_call = smpboot_thread_call, - .priority = CPU_PRI_SMPBOOT, -}; - -void smpboot_thread_init(void) +/* + * Called from the idle task. We need to set active here, so we can kick off + * the stopper thread and unpark the smpboot threads. If the target state is + * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the + * cpu further. + */ +void cpuhp_online_idle(enum cpuhp_state state) { - register_cpu_notifier(&smpboot_thread_notifier); + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + unsigned int cpu = smp_processor_id(); + + /* Happens for the boot cpu */ + if (state != CPUHP_AP_ONLINE_IDLE) + return; + + st->state = CPUHP_AP_ONLINE_IDLE; + + /* The cpu is marked online, set it active now */ + set_cpu_active(cpu, true); + /* Unpark the stopper thread and the hotplug thread of this cpu */ + stop_machine_unpark(cpu); + kthread_unpark(st->thread); + + /* Should we go further up ? */ + if (st->target > CPUHP_AP_ONLINE_IDLE) + __cpuhp_kick_ap_work(st); + else + complete(&st->done); } /* Requires cpu_add_remove_lock to be held */ -static int _cpu_up(unsigned int cpu, int tasks_frozen) +static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { - int ret, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; + int ret = 0; cpu_hotplug_begin(); - if (cpu_online(cpu) || !cpu_present(cpu)) { + if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } - idle = idle_thread_get(cpu); - if (IS_ERR(idle)) { - ret = PTR_ERR(idle); - goto out; - } - - ret = smpboot_create_threads(cpu); - if (ret) + /* + * The caller of do_cpu_up might have raced with another + * caller. Ignore it for now. + */ + if (st->state >= target) goto out; - ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); - if (ret) { - nr_calls--; - pr_warn("%s: attempt to bring up CPU %u failed\n", - __func__, cpu); - goto out_notify; + if (st->state == CPUHP_OFFLINE) { + /* Let it fail before we try to bring the cpu up */ + idle = idle_thread_get(cpu); + if (IS_ERR(idle)) { + ret = PTR_ERR(idle); + goto out; + } } - /* Arch-specific enabling code. */ - ret = __cpu_up(cpu, idle); - - if (ret != 0) - goto out_notify; - BUG_ON(!cpu_online(cpu)); + cpuhp_tasks_frozen = tasks_frozen; - /* Now call notifier in preparation. */ - cpu_notify(CPU_ONLINE | mod, hcpu); + st->target = target; + /* + * If the current CPU state is in the range of the AP hotplug thread, + * then we need to kick the thread once more. + */ + if (st->state > CPUHP_BRINGUP_CPU) { + ret = cpuhp_kick_ap_work(cpu); + /* + * The AP side has done the error rollback already. Just + * return the error code.. + */ + if (ret) + goto out; + } -out_notify: - if (ret != 0) - __cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL); + /* + * Try to reach the target state. We max out on the BP at + * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is + * responsible for bringing it up to the target state. + */ + target = min((int)target, CPUHP_BRINGUP_CPU); + ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target); out: cpu_hotplug_done(); - return ret; } -int cpu_up(unsigned int cpu) +static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; @@ -558,12 +1001,16 @@ int cpu_up(unsigned int cpu) goto out; } - err = _cpu_up(cpu, 0); - + err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } + +int cpu_up(unsigned int cpu) +{ + return do_cpu_up(cpu, CPUHP_ONLINE); +} EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP @@ -586,7 +1033,7 @@ int disable_nonboot_cpus(void) if (cpu == first_cpu) continue; trace_suspend_resume(TPS("CPU_OFF"), cpu, true); - error = _cpu_down(cpu, 1); + error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); @@ -636,7 +1083,7 @@ void enable_nonboot_cpus(void) for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); - error = _cpu_up(cpu, 1); + error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); @@ -709,26 +1156,463 @@ core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ +#endif /* CONFIG_SMP */ + +/* Boot processor state steps */ +static struct cpuhp_step cpuhp_bp_states[] = { + [CPUHP_OFFLINE] = { + .name = "offline", + .startup = NULL, + .teardown = NULL, + }, +#ifdef CONFIG_SMP + [CPUHP_CREATE_THREADS]= { + .name = "threads:create", + .startup = smpboot_create_threads, + .teardown = NULL, + .cant_stop = true, + }, + /* + * Preparatory and dead notifiers. Will be replaced once the notifiers + * are converted to states. + */ + [CPUHP_NOTIFY_PREPARE] = { + .name = "notify:prepare", + .startup = notify_prepare, + .teardown = notify_dead, + .skip_onerr = true, + .cant_stop = true, + }, + /* Kicks the plugged cpu into life */ + [CPUHP_BRINGUP_CPU] = { + .name = "cpu:bringup", + .startup = bringup_cpu, + .teardown = NULL, + .cant_stop = true, + }, + /* + * Handled on controll processor until the plugged processor manages + * this itself. + */ + [CPUHP_TEARDOWN_CPU] = { + .name = "cpu:teardown", + .startup = NULL, + .teardown = takedown_cpu, + .cant_stop = true, + }, +#endif +}; + +/* Application processor state steps */ +static struct cpuhp_step cpuhp_ap_states[] = { +#ifdef CONFIG_SMP + /* Final state before CPU kills itself */ + [CPUHP_AP_IDLE_DEAD] = { + .name = "idle:dead", + }, + /* + * Last state before CPU enters the idle loop to die. Transient state + * for synchronization. + */ + [CPUHP_AP_OFFLINE] = { + .name = "ap:offline", + .cant_stop = true, + }, + /* + * Low level startup/teardown notifiers. Run with interrupts + * disabled. Will be removed once the notifiers are converted to + * states. + */ + [CPUHP_AP_NOTIFY_STARTING] = { + .name = "notify:starting", + .startup = notify_starting, + .teardown = notify_dying, + .skip_onerr = true, + .cant_stop = true, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient + * state for synchronsization */ + [CPUHP_AP_ONLINE] = { + .name = "ap:online", + }, + /* Handle smpboot threads park/unpark */ + [CPUHP_AP_SMPBOOT_THREADS] = { + .name = "smpboot:threads", + .startup = smpboot_unpark_threads, + .teardown = NULL, + }, + /* + * Online/down_prepare notifiers. Will be removed once the notifiers + * are converted to states. + */ + [CPUHP_AP_NOTIFY_ONLINE] = { + .name = "notify:online", + .startup = notify_online, + .teardown = notify_down_prepare, + }, +#endif + /* + * The dynamically registered state space is here + */ + + /* CPU is fully up and running. */ + [CPUHP_ONLINE] = { + .name = "online", + .startup = NULL, + .teardown = NULL, + }, +}; + +/* Sanity check for callbacks */ +static int cpuhp_cb_check(enum cpuhp_state state) +{ + if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) + return -EINVAL; + return 0; +} + +static bool cpuhp_is_ap_state(enum cpuhp_state state) +{ + /* + * The extra check for CPUHP_TEARDOWN_CPU is only for documentation + * purposes as that state is handled explicitely in cpu_down. + */ + return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; +} + +static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) +{ + struct cpuhp_step *sp; + + sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states; + return sp + state; +} + +static void cpuhp_store_callbacks(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + /* (Un)Install the callbacks for further cpu hotplug operations */ + struct cpuhp_step *sp; + + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(state); + sp->startup = startup; + sp->teardown = teardown; + sp->name = name; + mutex_unlock(&cpuhp_state_mutex); +} + +static void *cpuhp_get_teardown_cb(enum cpuhp_state state) +{ + return cpuhp_get_step(state)->teardown; +} + +/* + * Call the startup/teardown function for a step either on the AP or + * on the current CPU. + */ +static int cpuhp_issue_call(int cpu, enum cpuhp_state state, + int (*cb)(unsigned int), bool bringup) +{ + int ret; + + if (!cb) + return 0; + /* + * The non AP bound callbacks can fail on bringup. On teardown + * e.g. module removal we crash for now. + */ +#ifdef CONFIG_SMP + if (cpuhp_is_ap_state(state)) + ret = cpuhp_invoke_ap_callback(cpu, state, cb); + else + ret = cpuhp_invoke_callback(cpu, state, cb); +#else + ret = cpuhp_invoke_callback(cpu, state, cb); +#endif + BUG_ON(ret && !bringup); + return ret; +} + +/* + * Called from __cpuhp_setup_state on a recoverable failure. + * + * Note: The teardown callbacks for rollback are not allowed to fail! + */ +static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, + int (*teardown)(unsigned int cpu)) +{ + int cpu; + + if (!teardown) + return; + + /* Roll back the already executed steps on the other cpus */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpu >= failedcpu) + break; + + /* Did we invoke the startup call on that cpu ? */ + if (cpustate >= state) + cpuhp_issue_call(cpu, state, teardown, false); + } +} + +/* + * Returns a free for dynamic slot assignment of the Online state. The states + * are protected by the cpuhp_slot_states mutex and an empty slot is identified + * by having no name assigned. + */ +static int cpuhp_reserve_state(enum cpuhp_state state) +{ + enum cpuhp_state i; + + mutex_lock(&cpuhp_state_mutex); + for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) { + if (cpuhp_ap_states[i].name) + continue; + + cpuhp_ap_states[i].name = "Reserved"; + mutex_unlock(&cpuhp_state_mutex); + return i; + } + mutex_unlock(&cpuhp_state_mutex); + WARN(1, "No more dynamic states available for CPU hotplug\n"); + return -ENOSPC; +} + /** - * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers - * @cpu: cpu that just started + * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state + * @state: The state to setup + * @invoke: If true, the startup function is invoked for cpus where + * cpu state >= @state + * @startup: startup callback function + * @teardown: teardown callback function * - * This function calls the cpu_chain notifiers with CPU_STARTING. - * It must be called by the arch code on the new cpu, before the new cpu - * enables interrupts and before the "boot" cpu returns from __cpu_up(). + * Returns 0 if successful, otherwise a proper error code */ -void notify_cpu_starting(unsigned int cpu) +int __cpuhp_setup_state(enum cpuhp_state state, + const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) { - unsigned long val = CPU_STARTING; + int cpu, ret = 0; + int dyn_state = 0; -#ifdef CONFIG_PM_SLEEP_SMP - if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus)) - val = CPU_STARTING_FROZEN; -#endif /* CONFIG_PM_SLEEP_SMP */ - cpu_notify(val, (void *)(long)cpu); + if (cpuhp_cb_check(state) || !name) + return -EINVAL; + + get_online_cpus(); + + /* currently assignments for the ONLINE state are possible */ + if (state == CPUHP_AP_ONLINE_DYN) { + dyn_state = 1; + ret = cpuhp_reserve_state(state); + if (ret < 0) + goto out; + state = ret; + } + + cpuhp_store_callbacks(state, name, startup, teardown); + + if (!invoke || !startup) + goto out; + + /* + * Try to call the startup callback for each present cpu + * depending on the hotplug state of the cpu. + */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpustate < state) + continue; + + ret = cpuhp_issue_call(cpu, state, startup, true); + if (ret) { + cpuhp_rollback_install(cpu, state, teardown); + cpuhp_store_callbacks(state, NULL, NULL, NULL); + goto out; + } + } +out: + put_online_cpus(); + if (!ret && dyn_state) + return state; + return ret; } +EXPORT_SYMBOL(__cpuhp_setup_state); -#endif /* CONFIG_SMP */ +/** + * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state + * @state: The state to remove + * @invoke: If true, the teardown function is invoked for cpus where + * cpu state >= @state + * + * The teardown callback is currently not allowed to fail. Think + * about module removal! + */ +void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) +{ + int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state); + int cpu; + + BUG_ON(cpuhp_cb_check(state)); + + get_online_cpus(); + + if (!invoke || !teardown) + goto remove; + + /* + * Call the teardown callback for each present cpu depending + * on the hotplug state of the cpu. This function is not + * allowed to fail currently! + */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpustate >= state) + cpuhp_issue_call(cpu, state, teardown, false); + } +remove: + cpuhp_store_callbacks(state, NULL, NULL, NULL); + put_online_cpus(); +} +EXPORT_SYMBOL(__cpuhp_remove_state); + +#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) +static ssize_t show_cpuhp_state(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->state); +} +static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL); + +static ssize_t write_cpuhp_target(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int target, ret; + + ret = kstrtoint(buf, 10, &target); + if (ret) + return ret; + +#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL + if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) + return -EINVAL; +#else + if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) + return -EINVAL; +#endif + + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(target); + ret = !sp->name || sp->cant_stop ? -EINVAL : 0; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + if (st->state < target) + ret = do_cpu_up(dev->id, target); + else + ret = do_cpu_down(dev->id, target); + + unlock_device_hotplug(); + return ret ? ret : count; +} + +static ssize_t show_cpuhp_target(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->target); +} +static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static struct attribute *cpuhp_cpu_attrs[] = { + &dev_attr_state.attr, + &dev_attr_target.attr, + NULL +}; + +static struct attribute_group cpuhp_cpu_attr_group = { + .attrs = cpuhp_cpu_attrs, + .name = "hotplug", + NULL +}; + +static ssize_t show_cpuhp_states(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t cur, res = 0; + int i; + + mutex_lock(&cpuhp_state_mutex); + for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { + struct cpuhp_step *sp = cpuhp_get_step(i); + + if (sp->name) { + cur = sprintf(buf, "%3d: %s\n", i, sp->name); + buf += cur; + res += cur; + } + } + mutex_unlock(&cpuhp_state_mutex); + return res; +} +static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL); + +static struct attribute *cpuhp_cpu_root_attrs[] = { + &dev_attr_states.attr, + NULL +}; + +static struct attribute_group cpuhp_cpu_root_attr_group = { + .attrs = cpuhp_cpu_root_attrs, + .name = "hotplug", + NULL +}; + +static int __init cpuhp_sysfs_init(void) +{ + int cpu, ret; + + ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpuhp_cpu_root_attr_group); + if (ret) + return ret; + + for_each_possible_cpu(cpu) { + struct device *dev = get_cpu_device(cpu); + + if (!dev) + continue; + ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); + if (ret) + return ret; + } + return 0; +} +device_initcall(cpuhp_sysfs_init); +#endif /* * cpu_bit_bitmap[] is a special, "compressed" data structure that @@ -789,3 +1673,25 @@ void init_cpu_online(const struct cpumask *src) { cpumask_copy(&__cpu_online_mask, src); } + +/* + * Activate the first processor. + */ +void __init boot_cpu_init(void) +{ + int cpu = smp_processor_id(); + + /* Mark the boot cpu "present", "online" etc for SMP and UP case */ + set_cpu_online(cpu, true); + set_cpu_active(cpu, true); + set_cpu_present(cpu, true); + set_cpu_possible(cpu, true); +} + +/* + * Must be called _AFTER_ setting up the per_cpu areas + */ +void __init boot_cpu_state_init(void) +{ + per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; +} diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index e1dbf4a..90ff129 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) } else { kdb_printf("%s: failed to set breakpoint at 0x%lx\n", __func__, bp->bp_addr); -#ifdef CONFIG_DEBUG_RODATA if (!bp->bp_type) { kdb_printf("Software breakpoints are unavailable.\n" - " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " Boot the kernel with rodata=off\n" " OR use hw breaks: help bph\n"); } -#endif return 1; } return 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index 6146148..712570d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3112,17 +3112,6 @@ done: return rotate; } -#ifdef CONFIG_NO_HZ_FULL -bool perf_event_can_stop_tick(void) -{ - if (atomic_read(&nr_freq_events) || - __this_cpu_read(perf_throttled_count)) - return false; - else - return true; -} -#endif - void perf_event_task_tick(void) { struct list_head *head = this_cpu_ptr(&active_ctx_list); @@ -3133,6 +3122,7 @@ void perf_event_task_tick(void) __this_cpu_inc(perf_throttled_seq); throttled = __this_cpu_xchg(perf_throttled_count, 0); + tick_dep_clear_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); list_for_each_entry_safe(ctx, tmp, head, active_ctx_list) perf_adjust_freq_unthr_context(ctx, throttled); @@ -3564,6 +3554,28 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) atomic_dec(&per_cpu(perf_cgroup_events, cpu)); } +#ifdef CONFIG_NO_HZ_FULL +static DEFINE_SPINLOCK(nr_freq_lock); +#endif + +static void unaccount_freq_event_nohz(void) +{ +#ifdef CONFIG_NO_HZ_FULL + spin_lock(&nr_freq_lock); + if (atomic_dec_and_test(&nr_freq_events)) + tick_nohz_dep_clear(TICK_DEP_BIT_PERF_EVENTS); + spin_unlock(&nr_freq_lock); +#endif +} + +static void unaccount_freq_event(void) +{ + if (tick_nohz_full_enabled()) + unaccount_freq_event_nohz(); + else + atomic_dec(&nr_freq_events); +} + static void unaccount_event(struct perf_event *event) { bool dec = false; @@ -3580,7 +3592,7 @@ static void unaccount_event(struct perf_event *event) if (event->attr.task) atomic_dec(&nr_task_events); if (event->attr.freq) - atomic_dec(&nr_freq_events); + unaccount_freq_event(); if (event->attr.context_switch) { dec = true; atomic_dec(&nr_switch_events); @@ -6424,9 +6436,9 @@ static int __perf_event_overflow(struct perf_event *event, if (unlikely(throttle && hwc->interrupts >= max_samples_per_tick)) { __this_cpu_inc(perf_throttled_count); + tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); hwc->interrupts = MAX_INTERRUPTS; perf_log_throttle(event, 0); - tick_nohz_full_kick(); ret = 1; } } @@ -6785,7 +6797,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash) kfree_rcu(hlist, rcu_head); } -static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) +static void swevent_hlist_put_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -6797,15 +6809,15 @@ static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) mutex_unlock(&swhash->hlist_mutex); } -static void swevent_hlist_put(struct perf_event *event) +static void swevent_hlist_put(void) { int cpu; for_each_possible_cpu(cpu) - swevent_hlist_put_cpu(event, cpu); + swevent_hlist_put_cpu(cpu); } -static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) +static int swevent_hlist_get_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); int err = 0; @@ -6828,14 +6840,13 @@ exit: return err; } -static int swevent_hlist_get(struct perf_event *event) +static int swevent_hlist_get(void) { - int err; - int cpu, failed_cpu; + int err, cpu, failed_cpu; get_online_cpus(); for_each_possible_cpu(cpu) { - err = swevent_hlist_get_cpu(event, cpu); + err = swevent_hlist_get_cpu(cpu); if (err) { failed_cpu = cpu; goto fail; @@ -6848,7 +6859,7 @@ fail: for_each_possible_cpu(cpu) { if (cpu == failed_cpu) break; - swevent_hlist_put_cpu(event, cpu); + swevent_hlist_put_cpu(cpu); } put_online_cpus(); @@ -6864,7 +6875,7 @@ static void sw_perf_event_destroy(struct perf_event *event) WARN_ON(event->parent); static_key_slow_dec(&perf_swevent_enabled[event_id]); - swevent_hlist_put(event); + swevent_hlist_put(); } static int perf_swevent_init(struct perf_event *event) @@ -6895,7 +6906,7 @@ static int perf_swevent_init(struct perf_event *event) if (!event->parent) { int err; - err = swevent_hlist_get(event); + err = swevent_hlist_get(); if (err) return err; @@ -7816,6 +7827,27 @@ static void account_event_cpu(struct perf_event *event, int cpu) atomic_inc(&per_cpu(perf_cgroup_events, cpu)); } +/* Freq events need the tick to stay alive (see perf_event_task_tick). */ +static void account_freq_event_nohz(void) +{ +#ifdef CONFIG_NO_HZ_FULL + /* Lock so we don't race with concurrent unaccount */ + spin_lock(&nr_freq_lock); + if (atomic_inc_return(&nr_freq_events) == 1) + tick_nohz_dep_set(TICK_DEP_BIT_PERF_EVENTS); + spin_unlock(&nr_freq_lock); +#endif +} + +static void account_freq_event(void) +{ + if (tick_nohz_full_enabled()) + account_freq_event_nohz(); + else + atomic_inc(&nr_freq_events); +} + + static void account_event(struct perf_event *event) { bool inc = false; @@ -7831,10 +7863,8 @@ static void account_event(struct perf_event *event) atomic_inc(&nr_comm_events); if (event->attr.task) atomic_inc(&nr_task_events); - if (event->attr.freq) { - if (atomic_inc_return(&nr_freq_events) == 1) - tick_nohz_full_kick_all(); - } + if (event->attr.freq) + account_freq_event(); if (event->attr.context_switch) { atomic_inc(&nr_switch_events); inc = true; @@ -8001,6 +8031,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } } + /* symmetric to unaccount_event() in _free_event() */ + account_event(event); + return event; err_per_task: @@ -8364,8 +8397,6 @@ SYSCALL_DEFINE5(perf_event_open, } } - account_event(event); - /* * Special case software events and allow them to be part of * any hardware group. @@ -8662,8 +8693,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, /* Mark owner so we could distinguish it from user events. */ event->owner = TASK_TOMBSTONE; - account_event(event); - ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); @@ -9447,6 +9476,7 @@ ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, return 0; } +EXPORT_SYMBOL_GPL(perf_event_sysfs_show); static int __init perf_event_sysfs_init(void) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 0167679..5f6ce93 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1178,6 +1178,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) goto free_area; area->xol_mapping.name = "[uprobes]"; + area->xol_mapping.fault = NULL; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER); if (!area->pages[0]) diff --git a/kernel/futex.c b/kernel/futex.c index 5d6ce64..a5d2e74 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -124,16 +124,16 @@ * futex_wait(futex, val); * * waiters++; (a) - * mb(); (A) <-- paired with -. - * | - * lock(hash_bucket(futex)); | - * | - * uval = *futex; | - * | *futex = newval; - * | sys_futex(WAKE, futex); - * | futex_wake(futex); - * | - * `-------> mb(); (B) + * smp_mb(); (A) <-- paired with -. + * | + * lock(hash_bucket(futex)); | + * | + * uval = *futex; | + * | *futex = newval; + * | sys_futex(WAKE, futex); + * | futex_wake(futex); + * | + * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); @@ -334,7 +334,7 @@ static inline void futex_get_mm(union futex_key *key) /* * Ensure futex_get_mm() implies a full barrier such that * get_futex_key() implies a full barrier. This is relied upon - * as full barrier (B), see the ordering comment above. + * as smp_mb(); (B), see the ordering comment above. */ smp_mb__after_atomic(); } @@ -407,10 +407,10 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - ihold(key->shared.inode); /* implies MB (B) */ + ihold(key->shared.inode); /* implies smp_mb(); (B) */ break; case FUT_OFF_MMSHARED: - futex_get_mm(key); /* implies MB (B) */ + futex_get_mm(key); /* implies smp_mb(); (B) */ break; default: /* @@ -418,7 +418,7 @@ static void get_futex_key_refs(union futex_key *key) * mm, therefore the only purpose of calling get_futex_key_refs * is because we need the barrier for the lockless waiter check. */ - smp_mb(); /* explicit MB (B) */ + smp_mb(); /* explicit smp_mb(); (B) */ } } @@ -497,7 +497,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) if (!fshared) { key->private.mm = mm; key->private.address = address; - get_futex_key_refs(key); /* implies MB (B) */ + get_futex_key_refs(key); /* implies smp_mb(); (B) */ return 0; } @@ -520,7 +520,20 @@ again: else err = 0; - lock_page(page); + /* + * The treatment of mapping from this point on is critical. The page + * lock protects many things but in this context the page lock + * stabilizes mapping, prevents inode freeing in the shared + * file-backed region case and guards against movement to swap cache. + * + * Strictly speaking the page lock is not needed in all cases being + * considered here and page lock forces unnecessarily serialization + * From this point on, mapping will be re-verified if necessary and + * page lock will be acquired only if it is unavoidable + */ + page = compound_head(page); + mapping = READ_ONCE(page->mapping); + /* * If page->mapping is NULL, then it cannot be a PageAnon * page; but it might be the ZERO_PAGE or in the gate area or @@ -536,19 +549,31 @@ again: * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for page->mapping. */ - mapping = compound_head(page)->mapping; - if (!mapping) { - int shmem_swizzled = PageSwapCache(page); + if (unlikely(!mapping)) { + int shmem_swizzled; + + /* + * Page lock is required to identify which special case above + * applies. If this is really a shmem page then the page lock + * will prevent unexpected transitions. + */ + lock_page(page); + shmem_swizzled = PageSwapCache(page) || page->mapping; unlock_page(page); put_page(page); + if (shmem_swizzled) goto again; + return -EFAULT; } /* * Private mappings are handled in a simple way. * + * If the futex key is stored on an anonymous page, then the associated + * object is the mm which is implicitly pinned by the calling process. + * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. @@ -566,16 +591,74 @@ again: key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; + + get_futex_key_refs(key); /* implies smp_mb(); (B) */ + } else { + struct inode *inode; + + /* + * The associated futex object in this case is the inode and + * the page->mapping must be traversed. Ordinarily this should + * be stabilised under page lock but it's not strictly + * necessary in this case as we just want to pin the inode, not + * update the radix tree or anything like that. + * + * The RCU read lock is taken as the inode is finally freed + * under RCU. If the mapping still matches expectations then the + * mapping->host can be safely accessed as being a valid inode. + */ + rcu_read_lock(); + + if (READ_ONCE(page->mapping) != mapping) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + inode = READ_ONCE(mapping->host); + if (!inode) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + /* + * Take a reference unless it is about to be freed. Previously + * this reference was taken by ihold under the page lock + * pinning the inode in place so i_lock was unnecessary. The + * only way for this check to fail is if the inode was + * truncated in parallel so warn for now if this happens. + * + * We are not calling into get_futex_key_refs() in file-backed + * cases, therefore a successful atomic_inc return below will + * guarantee that get_futex_key() will still imply smp_mb(); (B). + */ + if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + /* Should be impossible but lets be paranoid for now */ + if (WARN_ON_ONCE(inode->i_mapping != mapping)) { + err = -EFAULT; + rcu_read_unlock(); + iput(inode); + + goto out; + } + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = mapping->host; + key->shared.inode = inode; key->shared.pgoff = basepage_index(page); + rcu_read_unlock(); } - get_futex_key_refs(key); /* implies MB (B) */ - out: - unlock_page(page); put_page(page); return err; } @@ -1864,7 +1947,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); /* implies MB (A) */ + spin_lock(&hb->lock); /* implies smp_mb(); (A) */ return hb; } @@ -1927,8 +2010,12 @@ static int unqueue_me(struct futex_q *q) /* In the common case we don't take the spinlock, which is nice. */ retry: - lock_ptr = q->lock_ptr; - barrier(); + /* + * q->lock_ptr can change between this read and the following spin_lock. + * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and + * optimizing lock_ptr out of the logic below. + */ + lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 3b48dab..3bbfd6a 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -64,6 +64,10 @@ config IRQ_DOMAIN_HIERARCHY bool select IRQ_DOMAIN +# Generic IRQ IPI support +config GENERIC_IRQ_IPI + bool + # Generic MSI interrupt support config GENERIC_MSI_IRQ bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 2fc9cbd..2ee42e9 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -8,3 +8,4 @@ obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o +obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 5797909..2f9f2b0 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -961,6 +961,7 @@ void irq_chip_mask_parent(struct irq_data *data) data = data->parent_data; data->chip->irq_mask(data); } +EXPORT_SYMBOL_GPL(irq_chip_mask_parent); /** * irq_chip_unmask_parent - Unmask the parent interrupt @@ -971,6 +972,7 @@ void irq_chip_unmask_parent(struct irq_data *data) data = data->parent_data; data->chip->irq_unmask(data); } +EXPORT_SYMBOL_GPL(irq_chip_unmask_parent); /** * irq_chip_eoi_parent - Invoke EOI on the parent interrupt @@ -981,6 +983,7 @@ void irq_chip_eoi_parent(struct irq_data *data) data = data->parent_data; data->chip->irq_eoi(data); } +EXPORT_SYMBOL_GPL(irq_chip_eoi_parent); /** * irq_chip_set_affinity_parent - Set affinity on the parent interrupt @@ -1016,6 +1019,7 @@ int irq_chip_set_type_parent(struct irq_data *data, unsigned int type) return -ENOSYS; } +EXPORT_SYMBOL_GPL(irq_chip_set_type_parent); /** * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 57bff78..a15b548 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -136,10 +136,9 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval = IRQ_NONE; unsigned int flags = 0, irq = desc->irq_data.irq; - struct irqaction *action = desc->action; + struct irqaction *action; - /* action might have become NULL since we dropped the lock */ - while (action) { + for_each_action_of_desc(desc, action) { irqreturn_t res; trace_irq_handler_entry(irq, action); @@ -173,7 +172,6 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) } retval |= res; - action = action->next; } add_interrupt_randomness(irq, flags); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index fcab63c..09be2c9 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -131,6 +131,9 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc) #define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) #define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) +#define for_each_action_of_desc(desc, act) \ + for (act = desc->act; act; act = act->next) + struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check); @@ -160,6 +163,8 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) __irq_put_desc_unlock(desc, flags, false); } +#define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) + /* * Manipulation functions for irq_data.state */ @@ -188,6 +193,8 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) return __irqd_to_state(d) & mask; } +#undef __irqd_to_state + static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __this_cpu_inc(*desc->kstat_irqs); diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c new file mode 100644 index 0000000..c37f34b --- /dev/null +++ b/kernel/irq/ipi.c @@ -0,0 +1,326 @@ +/* + * linux/kernel/irq/ipi.c + * + * Copyright (C) 2015 Imagination Technologies Ltd + * Author: Qais Yousef <qais.yousef@imgtec.com> + * + * This file contains driver APIs to the IPI subsystem. + */ + +#define pr_fmt(fmt) "genirq/ipi: " fmt + +#include <linux/irqdomain.h> +#include <linux/irq.h> + +/** + * irq_reserve_ipi() - Setup an IPI to destination cpumask + * @domain: IPI domain + * @dest: cpumask of cpus which can receive the IPI + * + * Allocate a virq that can be used to send IPI to any CPU in dest mask. + * + * On success it'll return linux irq number and 0 on failure + */ +unsigned int irq_reserve_ipi(struct irq_domain *domain, + const struct cpumask *dest) +{ + unsigned int nr_irqs, offset; + struct irq_data *data; + int virq, i; + + if (!domain ||!irq_domain_is_ipi(domain)) { + pr_warn("Reservation on a non IPI domain\n"); + return 0; + } + + if (!cpumask_subset(dest, cpu_possible_mask)) { + pr_warn("Reservation is not in possible_cpu_mask\n"); + return 0; + } + + nr_irqs = cpumask_weight(dest); + if (!nr_irqs) { + pr_warn("Reservation for empty destination mask\n"); + return 0; + } + + if (irq_domain_is_ipi_single(domain)) { + /* + * If the underlying implementation uses a single HW irq on + * all cpus then we only need a single Linux irq number for + * it. We have no restrictions vs. the destination mask. The + * underlying implementation can deal with holes nicely. + */ + nr_irqs = 1; + offset = 0; + } else { + unsigned int next; + + /* + * The IPI requires a seperate HW irq on each CPU. We require + * that the destination mask is consecutive. If an + * implementation needs to support holes, it can reserve + * several IPI ranges. + */ + offset = cpumask_first(dest); + /* + * Find a hole and if found look for another set bit after the + * hole. For now we don't support this scenario. + */ + next = cpumask_next_zero(offset, dest); + if (next < nr_cpu_ids) + next = cpumask_next(next, dest); + if (next < nr_cpu_ids) { + pr_warn("Destination mask has holes\n"); + return 0; + } + } + + virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE); + if (virq <= 0) { + pr_warn("Can't reserve IPI, failed to alloc descs\n"); + return 0; + } + + virq = __irq_domain_alloc_irqs(domain, virq, nr_irqs, NUMA_NO_NODE, + (void *) dest, true); + + if (virq <= 0) { + pr_warn("Can't reserve IPI, failed to alloc hw irqs\n"); + goto free_descs; + } + + for (i = 0; i < nr_irqs; i++) { + data = irq_get_irq_data(virq + i); + cpumask_copy(data->common->affinity, dest); + data->common->ipi_offset = offset; + } + return virq; + +free_descs: + irq_free_descs(virq, nr_irqs); + return 0; +} + +/** + * irq_destroy_ipi() - unreserve an IPI that was previously allocated + * @irq: linux irq number to be destroyed + * + * Return the IPIs allocated with irq_reserve_ipi() to the system destroying + * all virqs associated with them. + */ +void irq_destroy_ipi(unsigned int irq) +{ + struct irq_data *data = irq_get_irq_data(irq); + struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; + struct irq_domain *domain; + unsigned int nr_irqs; + + if (!irq || !data || !ipimask) + return; + + domain = data->domain; + if (WARN_ON(domain == NULL)) + return; + + if (!irq_domain_is_ipi(domain)) { + pr_warn("Trying to destroy a non IPI domain!\n"); + return; + } + + if (irq_domain_is_ipi_per_cpu(domain)) + nr_irqs = cpumask_weight(ipimask); + else + nr_irqs = 1; + + irq_domain_free_irqs(irq, nr_irqs); +} + +/** + * ipi_get_hwirq - Get the hwirq associated with an IPI to a cpu + * @irq: linux irq number + * @cpu: the target cpu + * + * When dealing with coprocessors IPI, we need to inform the coprocessor of + * the hwirq it needs to use to receive and send IPIs. + * + * Returns hwirq value on success and INVALID_HWIRQ on failure. + */ +irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu) +{ + struct irq_data *data = irq_get_irq_data(irq); + struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; + + if (!data || !ipimask || cpu > nr_cpu_ids) + return INVALID_HWIRQ; + + if (!cpumask_test_cpu(cpu, ipimask)) + return INVALID_HWIRQ; + + /* + * Get the real hardware irq number if the underlying implementation + * uses a seperate irq per cpu. If the underlying implementation uses + * a single hardware irq for all cpus then the IPI send mechanism + * needs to take care of the cpu destinations. + */ + if (irq_domain_is_ipi_per_cpu(data->domain)) + data = irq_get_irq_data(irq + cpu - data->common->ipi_offset); + + return data ? irqd_to_hwirq(data) : INVALID_HWIRQ; +} +EXPORT_SYMBOL_GPL(ipi_get_hwirq); + +static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, + const struct cpumask *dest, unsigned int cpu) +{ + struct cpumask *ipimask = irq_data_get_affinity_mask(data); + + if (!chip || !ipimask) + return -EINVAL; + + if (!chip->ipi_send_single && !chip->ipi_send_mask) + return -EINVAL; + + if (cpu > nr_cpu_ids) + return -EINVAL; + + if (dest) { + if (!cpumask_subset(dest, ipimask)) + return -EINVAL; + } else { + if (!cpumask_test_cpu(cpu, ipimask)) + return -EINVAL; + } + return 0; +} + +/** + * __ipi_send_single - send an IPI to a target Linux SMP CPU + * @desc: pointer to irq_desc of the IRQ + * @cpu: destination CPU, must in the destination mask passed to + * irq_reserve_ipi() + * + * This function is for architecture or core code to speed up IPI sending. Not + * usable from driver code. + * + * Returns zero on success and negative error number on failure. + */ +int __ipi_send_single(struct irq_desc *desc, unsigned int cpu) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_chip *chip = irq_data_get_irq_chip(data); + +#ifdef DEBUG + /* + * Minimise the overhead by omitting the checks for Linux SMP IPIs. + * Since the callers should be arch or core code which is generally + * trusted, only check for errors when debugging. + */ + if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu))) + return -EINVAL; +#endif + if (!chip->ipi_send_single) { + chip->ipi_send_mask(data, cpumask_of(cpu)); + return 0; + } + + /* FIXME: Store this information in irqdata flags */ + if (irq_domain_is_ipi_per_cpu(data->domain) && + cpu != data->common->ipi_offset) { + /* use the correct data for that cpu */ + unsigned irq = data->irq + cpu - data->common->ipi_offset; + + data = irq_get_irq_data(irq); + } + chip->ipi_send_single(data, cpu); + return 0; +} + +/** + * ipi_send_mask - send an IPI to target Linux SMP CPU(s) + * @desc: pointer to irq_desc of the IRQ + * @dest: dest CPU(s), must be a subset of the mask passed to + * irq_reserve_ipi() + * + * This function is for architecture or core code to speed up IPI sending. Not + * usable from driver code. + * + * Returns zero on success and negative error number on failure. + */ +int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_chip *chip = irq_data_get_irq_chip(data); + unsigned int cpu; + +#ifdef DEBUG + /* + * Minimise the overhead by omitting the checks for Linux SMP IPIs. + * Since the callers should be arch or core code which is generally + * trusted, only check for errors when debugging. + */ + if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0))) + return -EINVAL; +#endif + if (chip->ipi_send_mask) { + chip->ipi_send_mask(data, dest); + return 0; + } + + if (irq_domain_is_ipi_per_cpu(data->domain)) { + unsigned int base = data->irq; + + for_each_cpu(cpu, dest) { + unsigned irq = base + cpu - data->common->ipi_offset; + + data = irq_get_irq_data(irq); + chip->ipi_send_single(data, cpu); + } + } else { + for_each_cpu(cpu, dest) + chip->ipi_send_single(data, cpu); + } + return 0; +} + +/** + * ipi_send_single - Send an IPI to a single CPU + * @virq: linux irq number from irq_reserve_ipi() + * @cpu: destination CPU, must in the destination mask passed to + * irq_reserve_ipi() + * + * Returns zero on success and negative error number on failure. + */ +int ipi_send_single(unsigned int virq, unsigned int cpu) +{ + struct irq_desc *desc = irq_to_desc(virq); + struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL; + struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL; + + if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu))) + return -EINVAL; + + return __ipi_send_single(desc, cpu); +} +EXPORT_SYMBOL_GPL(ipi_send_single); + +/** + * ipi_send_mask - Send an IPI to target CPU(s) + * @virq: linux irq number from irq_reserve_ipi() + * @dest: dest CPU(s), must be a subset of the mask passed to + * irq_reserve_ipi() + * + * Returns zero on success and negative error number on failure. + */ +int ipi_send_mask(unsigned int virq, const struct cpumask *dest) +{ + struct irq_desc *desc = irq_to_desc(virq); + struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL; + struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL; + + if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0))) + return -EINVAL; + + return __ipi_send_mask(desc, dest); +} +EXPORT_SYMBOL_GPL(ipi_send_mask); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0409da0..0ccd028 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -24,10 +24,27 @@ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) +static int __init irq_affinity_setup(char *str) +{ + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); + cpulist_parse(str, irq_default_affinity); + /* + * Set at least the boot cpu. We don't want to end up with + * bugreports caused by random comandline masks + */ + cpumask_set_cpu(smp_processor_id(), irq_default_affinity); + return 1; +} +__setup("irqaffinity=", irq_affinity_setup); + static void __init init_irq_default_affinity(void) { - alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); - cpumask_setall(irq_default_affinity); +#ifdef CONFIG_CPUMASK_OFFSTACK + if (!irq_default_affinity) + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); +#endif + if (cpumask_empty(irq_default_affinity)) + cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 3e56d2f0..3a519a0 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -23,8 +23,6 @@ static DEFINE_MUTEX(irq_domain_mutex); static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_domain *irq_default_domain; -static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, - irq_hw_number_t hwirq, int node); static void irq_domain_check_hierarchy(struct irq_domain *domain); struct irqchip_fwid { @@ -840,8 +838,8 @@ const struct irq_domain_ops irq_domain_simple_ops = { }; EXPORT_SYMBOL_GPL(irq_domain_simple_ops); -static int irq_domain_alloc_descs(int virq, unsigned int cnt, - irq_hw_number_t hwirq, int node) +int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq, + int node) { unsigned int hint; @@ -895,6 +893,7 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, return domain; } +EXPORT_SYMBOL_GPL(irq_domain_create_hierarchy); static void irq_domain_insert_irq(int virq) { @@ -1045,6 +1044,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, return 0; } +EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip); /** * irq_domain_set_info - Set the complete data for a @virq in @domain @@ -1078,6 +1078,7 @@ void irq_domain_reset_irq_data(struct irq_data *irq_data) irq_data->chip = &no_irq_chip; irq_data->chip_data = NULL; } +EXPORT_SYMBOL_GPL(irq_domain_reset_irq_data); /** * irq_domain_free_irqs_common - Clear irq_data and free the parent @@ -1275,6 +1276,7 @@ int irq_domain_alloc_irqs_parent(struct irq_domain *domain, nr_irqs, arg); return -ENOSYS; } +EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent); /** * irq_domain_free_irqs_parent - Free interrupts from parent domain @@ -1292,6 +1294,7 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, irq_domain_free_irqs_recursive(domain->parent, irq_base, nr_irqs); } +EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); /** * irq_domain_activate_irq - Call domain_ops->activate recursively to activate diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 8411872..3ddd229 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -144,13 +144,11 @@ int irq_can_set_affinity(unsigned int irq) */ void irq_set_thread_affinity(struct irq_desc *desc) { - struct irqaction *action = desc->action; + struct irqaction *action; - while (action) { + for_each_action_of_desc(desc, action) if (action->thread) set_bit(IRQTF_AFFINITY, &action->thread_flags); - action = action->next; - } } #ifdef CONFIG_GENERIC_PENDING_IRQ @@ -994,7 +992,7 @@ void irq_wake_thread(unsigned int irq, void *dev_id) return; raw_spin_lock_irqsave(&desc->lock, flags); - for (action = desc->action; action; action = action->next) { + for_each_action_of_desc(desc, action) { if (action->dev_id == dev_id) { if (action->thread) __irq_wake_thread(desc, action); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index a2c02fd..4e1b947 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -291,7 +291,7 @@ static int name_unique(unsigned int irq, struct irqaction *new_action) int ret = 1; raw_spin_lock_irqsave(&desc->lock, flags); - for (action = desc->action ; action; action = action->next) { + for_each_action_of_desc(desc, action) { if ((action != new_action) && action->name && !strcmp(new_action->name, action->name)) { ret = 0; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 3214417..5707f97 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -211,14 +211,12 @@ static void __report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret) * desc->lock here. See synchronize_irq(). */ raw_spin_lock_irqsave(&desc->lock, flags); - action = desc->action; - while (action) { + for_each_action_of_desc(desc, action) { printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler); if (action->thread_fn) printk(KERN_CONT " threaded [<%p>] %pf", action->thread_fn, action->thread_fn); printk(KERN_CONT "\n"); - action = action->next; } raw_spin_unlock_irqrestore(&desc->lock, flags); } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 8dc6591..8d34308 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -66,13 +66,15 @@ struct resource crashk_res = { .name = "Crash kernel", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL }; struct resource crashk_low_res = { .name = "Crash kernel", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL }; int kexec_should_crash(struct task_struct *p) @@ -959,7 +961,7 @@ int crash_shrink_memory(unsigned long new_size) ram_res->start = end; ram_res->end = crashk_res.end; - ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; ram_res->name = "System RAM"; crashk_res.end = end - 1; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 007b791..56b18eb 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -524,10 +524,10 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz, /* Walk the RAM ranges and allocate a suitable range for the buffer */ if (image->type == KEXEC_TYPE_CRASH) - ret = walk_iomem_res("Crash kernel", - IORESOURCE_MEM | IORESOURCE_BUSY, - crashk_res.start, crashk_res.end, kbuf, - locate_mem_hole_callback); + ret = walk_iomem_res_desc(crashk_res.desc, + IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, + crashk_res.start, crashk_res.end, kbuf, + locate_mem_hole_callback); else ret = walk_system_ram_res(0, -1, kbuf, locate_mem_hole_callback); diff --git a/kernel/latencytop.c b/kernel/latencytop.c index a028127..b5c30d9 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -47,12 +47,12 @@ * of times) */ -#include <linux/latencytop.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/proc_fs.h> +#include <linux/latencytop.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/list.h> @@ -289,4 +289,16 @@ static int __init init_lstats_procfs(void) proc_create("latency_stats", 0644, NULL, &lstats_fops); return 0; } + +int sysctl_latencytop(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err; + + err = proc_dointvec(table, write, buffer, lenp, ppos); + if (latencytop_enabled) + force_schedstat_enabled(); + + return err; +} device_initcall(init_lstats_procfs); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 716547f..f894a2c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -123,8 +123,6 @@ static inline int debug_locks_off_graph_unlock(void) return ret; } -static int lockdep_initialized; - unsigned long nr_list_entries; static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; @@ -434,19 +432,6 @@ unsigned int max_lockdep_depth; #ifdef CONFIG_DEBUG_LOCKDEP /* - * We cannot printk in early bootup code. Not even early_printk() - * might work. So we mark any initialization errors and printk - * about it later on, in lockdep_info(). - */ -static int lockdep_init_error; -static const char *lock_init_error; -static unsigned long lockdep_init_trace_data[20]; -static struct stack_trace lockdep_init_trace = { - .max_entries = ARRAY_SIZE(lockdep_init_trace_data), - .entries = lockdep_init_trace_data, -}; - -/* * Various lockdep statistics: */ DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats); @@ -669,20 +654,6 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) struct hlist_head *hash_head; struct lock_class *class; -#ifdef CONFIG_DEBUG_LOCKDEP - /* - * If the architecture calls into lockdep before initializing - * the hashes then we'll warn about it later. (we cannot printk - * right now) - */ - if (unlikely(!lockdep_initialized)) { - lockdep_init(); - lockdep_init_error = 1; - lock_init_error = lock->name; - save_stack_trace(&lockdep_init_trace); - } -#endif - if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { debug_locks_off(); printk(KERN_ERR @@ -2011,6 +1982,53 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) } /* + * Returns the index of the first held_lock of the current chain + */ +static inline int get_first_held_lock(struct task_struct *curr, + struct held_lock *hlock) +{ + int i; + struct held_lock *hlock_curr; + + for (i = curr->lockdep_depth - 1; i >= 0; i--) { + hlock_curr = curr->held_locks + i; + if (hlock_curr->irq_context != hlock->irq_context) + break; + + } + + return ++i; +} + +/* + * Checks whether the chain and the current held locks are consistent + * in depth and also in content. If they are not it most likely means + * that there was a collision during the calculation of the chain_key. + * Returns: 0 not passed, 1 passed + */ +static int check_no_collision(struct task_struct *curr, + struct held_lock *hlock, + struct lock_chain *chain) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + int i, j, id; + + i = get_first_held_lock(curr, hlock); + + if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) + return 0; + + for (j = 0; j < chain->depth - 1; j++, i++) { + id = curr->held_locks[i].class_idx - 1; + + if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) + return 0; + } +#endif + return 1; +} + +/* * Look up a dependency chain. If the key is not present yet then * add it and return 1 - in this case the new dependency chain is * validated. If the key is already hashed, return 0. @@ -2023,7 +2041,6 @@ static inline int lookup_chain_cache(struct task_struct *curr, struct lock_class *class = hlock_class(hlock); struct hlist_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; - struct held_lock *hlock_curr; int i, j; /* @@ -2041,6 +2058,9 @@ static inline int lookup_chain_cache(struct task_struct *curr, if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); + if (!check_no_collision(curr, hlock, chain)) + return 0; + if (very_verbose(class)) printk("\nhash chain already cached, key: " "%016Lx tail class: [%p] %s\n", @@ -2078,13 +2098,7 @@ cache_hit: chain = lock_chains + nr_lock_chains++; chain->chain_key = chain_key; chain->irq_context = hlock->irq_context; - /* Find the first held_lock of current chain */ - for (i = curr->lockdep_depth - 1; i >= 0; i--) { - hlock_curr = curr->held_locks + i; - if (hlock_curr->irq_context != hlock->irq_context) - break; - } - i++; + i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; @@ -2172,7 +2186,7 @@ static void check_chain_key(struct task_struct *curr) { #ifdef CONFIG_DEBUG_LOCKDEP struct held_lock *hlock, *prev_hlock = NULL; - unsigned int i, id; + unsigned int i; u64 chain_key = 0; for (i = 0; i < curr->lockdep_depth; i++) { @@ -2189,17 +2203,16 @@ static void check_chain_key(struct task_struct *curr) (unsigned long long)hlock->prev_chain_key); return; } - id = hlock->class_idx - 1; /* * Whoops ran out of static storage again? */ - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + if (DEBUG_LOCKS_WARN_ON(hlock->class_idx > MAX_LOCKDEP_KEYS)) return; if (prev_hlock && (prev_hlock->irq_context != hlock->irq_context)) chain_key = 0; - chain_key = iterate_chain_key(chain_key, id); + chain_key = iterate_chain_key(chain_key, hlock->class_idx); prev_hlock = hlock; } if (chain_key != curr->curr_chain_key) { @@ -3077,7 +3090,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, struct task_struct *curr = current; struct lock_class *class = NULL; struct held_lock *hlock; - unsigned int depth, id; + unsigned int depth; int chain_head = 0; int class_idx; u64 chain_key; @@ -3180,11 +3193,10 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, * The 'key ID' is what is the most compact key value to drive * the hash, not class->key. */ - id = class - lock_classes; /* * Whoops, we did it again.. ran straight out of our static allocation. */ - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + if (DEBUG_LOCKS_WARN_ON(class_idx > MAX_LOCKDEP_KEYS)) return 0; chain_key = curr->curr_chain_key; @@ -3202,7 +3214,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, chain_key = 0; chain_head = 1; } - chain_key = iterate_chain_key(chain_key, id); + chain_key = iterate_chain_key(chain_key, class_idx); if (nest_lock && !__lock_is_held(nest_lock)) return print_lock_nested_lock_not_held(curr, hlock, ip); @@ -4013,28 +4025,6 @@ out_restore: raw_local_irq_restore(flags); } -void lockdep_init(void) -{ - int i; - - /* - * Some architectures have their own start_kernel() - * code which calls lockdep_init(), while we also - * call lockdep_init() from the start_kernel() itself, - * and we want to initialize the hashes only once: - */ - if (lockdep_initialized) - return; - - for (i = 0; i < CLASSHASH_SIZE; i++) - INIT_HLIST_HEAD(classhash_table + i); - - for (i = 0; i < CHAINHASH_SIZE; i++) - INIT_HLIST_HEAD(chainhash_table + i); - - lockdep_initialized = 1; -} - void __init lockdep_info(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); @@ -4061,14 +4051,6 @@ void __init lockdep_info(void) printk(" per task-struct memory footprint: %lu bytes\n", sizeof(struct held_lock) * MAX_LOCK_DEPTH); - -#ifdef CONFIG_DEBUG_LOCKDEP - if (lockdep_init_error) { - printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error); - printk("Call stack leading to lockdep invocation was:\n"); - print_stack_trace(&lockdep_init_trace, 0); - } -#endif } static void diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 5b9102a..c835270 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) node->locked = 0; node->next = NULL; - prev = xchg_acquire(lock, node); + /* + * We rely on the full barrier with global transitivity implied by the + * below xchg() to order the initialization stores above against any + * observation of @node. And to provide the ACQUIRE ordering associated + * with a LOCK primitive. + */ + prev = xchg(lock, node); if (likely(prev == NULL)) { /* * Lock acquired, don't need to set node->locked to 1. Threads diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 0551c21..e364b42 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -716,6 +716,7 @@ static inline void __mutex_unlock_common_slowpath(struct mutex *lock, int nested) { unsigned long flags; + WAKE_Q(wake_q); /* * As a performance measurement, release the lock before doing other @@ -743,11 +744,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested) struct mutex_waiter, list); debug_mutex_wake_waiter(lock, waiter); - - wake_up_process(waiter->task); + wake_q_add(&wake_q, waiter->task); } spin_unlock_mutex(&lock->wait_lock, flags); + wake_up_q(&wake_q); } /* diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 393d187..ce2f75e 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -358,8 +358,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * sequentiality; this is because not all clear_pending_set_locked() * implementations imply full barriers. */ - while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK) - cpu_relax(); + smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK)); /* * take ownership and clear the pending bit. @@ -435,7 +434,7 @@ queue: * * The PV pv_wait_head_or_lock function, if active, will acquire * the lock and return a non-zero value. So we have to skip the - * smp_load_acquire() call. As the next PV queue head hasn't been + * smp_cond_acquire() call. As the next PV queue head hasn't been * designated yet, there is no way for the locked value to become * _Q_SLOW_VAL. So both the set_locked() and the * atomic_cmpxchg_relaxed() calls will be safe. @@ -466,7 +465,7 @@ locked: break; } /* - * The smp_load_acquire() call above has provided the necessary + * The smp_cond_acquire() call above has provided the necessary * acquire semantics required for locking. At most two * iterations of this loop may be ran. */ diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 87bb235..21ede57 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -55,6 +55,11 @@ struct pv_node { }; /* + * Include queued spinlock statistics code + */ +#include "qspinlock_stat.h" + +/* * By replacing the regular queued_spin_trylock() with the function below, * it will be called once when a lock waiter enter the PV slowpath before * being queued. By allowing one lock stealing attempt here when the pending @@ -65,9 +70,11 @@ struct pv_node { static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock) { struct __qspinlock *l = (void *)lock; + int ret = !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && + (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0); - return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && - (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0); + qstat_inc(qstat_pv_lock_stealing, ret); + return ret; } /* @@ -138,11 +145,6 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock) #endif /* _Q_PENDING_BITS == 8 */ /* - * Include queued spinlock statistics code - */ -#include "qspinlock_stat.h" - -/* * Lock and MCS node addresses hash table for fast lookup * * Hashing is done on a per-cacheline basis to minimize the need to access @@ -398,6 +400,11 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) if (READ_ONCE(pn->state) == vcpu_hashed) lp = (struct qspinlock **)1; + /* + * Tracking # of slowpath locking operations + */ + qstat_inc(qstat_pv_lock_slowpath, true); + for (;; waitcnt++) { /* * Set correct vCPU state to be used by queue node wait-early diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 640dcec..eb2a2c9 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -22,6 +22,7 @@ * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake * pv_latency_kick - average latency (ns) of vCPU kick operation * pv_latency_wake - average latency (ns) from vCPU kick to wakeup + * pv_lock_slowpath - # of locking operations via the slowpath * pv_lock_stealing - # of lock stealing operations * pv_spurious_wakeup - # of spurious wakeups * pv_wait_again - # of vCPU wait's that happened after a vCPU kick @@ -45,6 +46,7 @@ enum qlock_stats { qstat_pv_kick_wake, qstat_pv_latency_kick, qstat_pv_latency_wake, + qstat_pv_lock_slowpath, qstat_pv_lock_stealing, qstat_pv_spurious_wakeup, qstat_pv_wait_again, @@ -70,6 +72,7 @@ static const char * const qstat_names[qstat_num + 1] = { [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup", [qstat_pv_latency_kick] = "pv_latency_kick", [qstat_pv_latency_wake] = "pv_latency_wake", + [qstat_pv_lock_slowpath] = "pv_lock_slowpath", [qstat_pv_lock_stealing] = "pv_lock_stealing", [qstat_pv_wait_again] = "pv_wait_again", [qstat_pv_wait_early] = "pv_wait_early", @@ -279,19 +282,6 @@ static inline void __pv_wait(u8 *ptr, u8 val) #define pv_kick(c) __pv_kick(c) #define pv_wait(p, v) __pv_wait(p, v) -/* - * PV unfair trylock count tracking function - */ -static inline int qstat_spin_steal_lock(struct qspinlock *lock) -{ - int ret = pv_queued_spin_steal_lock(lock); - - qstat_inc(qstat_pv_lock_stealing, ret); - return ret; -} -#undef queued_spin_trylock -#define queued_spin_trylock(l) qstat_spin_steal_lock(l) - #else /* CONFIG_QUEUED_LOCK_STAT */ static inline void qstat_inc(enum qlock_stats stat, bool cond) { } diff --git a/kernel/memremap.c b/kernel/memremap.c index b981a7b..fb9b887 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -29,10 +29,10 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) static void *try_ram_remap(resource_size_t offset, size_t size) { - struct page *page = pfn_to_page(offset >> PAGE_SHIFT); + unsigned long pfn = PHYS_PFN(offset); /* In the simple case just return the existing linear address */ - if (!PageHighMem(page)) + if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn))) return __va(offset); return NULL; /* fallback to ioremap_cache */ } @@ -47,7 +47,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * being mapped does not have i/o side effects and the __iomem * annotation is not applicable. * - * MEMREMAP_WB - matches the default mapping for "System RAM" on + * MEMREMAP_WB - matches the default mapping for System RAM on * the architecture. This is usually a read-allocate write-back cache. * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM * memremap() will bypass establishing a new mapping and instead return @@ -56,11 +56,12 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * MEMREMAP_WT - establish a mapping whereby writes either bypass the * cache or are written through to memory and never exist in a * cache-dirty state with respect to program visibility. Attempts to - * map "System RAM" with this mapping type will fail. + * map System RAM with this mapping type will fail. */ void *memremap(resource_size_t offset, size_t size, unsigned long flags) { - int is_ram = region_intersects(offset, size, "System RAM"); + int is_ram = region_intersects(offset, size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); void *addr = NULL; if (is_ram == REGION_MIXED) { @@ -76,7 +77,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * MEMREMAP_WB is special in that it can be satisifed * from the direct map. Some archs depend on the * capability of memremap() to autodetect cases where - * the requested range is potentially in "System RAM" + * the requested range is potentially in System RAM. */ if (is_ram == REGION_INTERSECTS) addr = try_ram_remap(offset, size); @@ -88,7 +89,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * If we don't have a mapping yet and more request flags are * pending then we will be attempting to establish a new virtual * address mapping. Enforce that this mapping is not aliasing - * "System RAM" + * System RAM. */ if (!addr && is_ram == REGION_INTERSECTS && flags) { WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", @@ -270,13 +271,17 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { - int is_ram = region_intersects(res->start, resource_size(res), - "System RAM"); resource_size_t key, align_start, align_size, align_end; struct dev_pagemap *pgmap; struct page_map *page_map; + int error, nid, is_ram; unsigned long pfn; - int error, nid; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) + - align_start; + is_ram = region_intersects(align_start, align_size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); if (is_ram == REGION_MIXED) { WARN_ONCE(1, "%s attempted on mixed region %pr\n", @@ -314,8 +319,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); align_end = align_start + align_size - 1; for (key = align_start; key <= align_end; key += SECTION_SIZE) { struct dev_pagemap *dup; @@ -351,8 +354,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, for_each_device_pfn(pfn, page_map) { struct page *page = pfn_to_page(pfn); - /* ZONE_DEVICE pages must never appear on a slab lru */ - list_force_poison(&page->lru); + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back + * pointer. It is a bug if a ZONE_DEVICE page is ever + * freed or placed on a driver-private list. Seed the + * storage with LIST_POISON* values. + */ + list_del(&page->lru); page->pgmap = pgmap; } devres_add(dev, page_map); diff --git a/kernel/profile.c b/kernel/profile.c index 99513e1..5136969 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -59,6 +59,7 @@ int profile_setup(char *str) if (!strncmp(str, sleepstr, strlen(sleepstr))) { #ifdef CONFIG_SCHEDSTATS + force_schedstat_enabled(); prof_on = SLEEP_PROFILING; if (str[strlen(sleepstr)] == ',') str += strlen(sleepstr) + 1; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index d2988d0..65ae0e5 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -932,12 +932,14 @@ rcu_torture_writer(void *arg) int nsynctypes = 0; VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); - pr_alert("%s" TORTURE_FLAG - " Grace periods expedited from boot/sysfs for %s,\n", - torture_type, cur_ops->name); - pr_alert("%s" TORTURE_FLAG - " Testing of dynamic grace-period expediting diabled.\n", - torture_type); + if (!can_expedite) { + pr_alert("%s" TORTURE_FLAG + " Grace periods expedited from boot/sysfs for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " Disabled dynamic grace-period expediting.\n", + torture_type); + } /* Initialize synctype[] array. If none set, take default. */ if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1) diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index e492a52..196f030 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -23,7 +23,7 @@ */ #include <linux/kthread.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -122,18 +122,7 @@ free_out: debugfs_remove_recursive(rcudir); return 1; } - -static void __exit rcutiny_trace_cleanup(void) -{ - debugfs_remove_recursive(rcudir); -} - -module_init(rcutiny_trace_init); -module_exit(rcutiny_trace_cleanup); - -MODULE_AUTHOR("Paul E. McKenney"); -MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation"); -MODULE_LICENSE("GPL"); +device_initcall(rcutiny_trace_init); static void check_cpu_stall(struct rcu_ctrlblk *rcp) { diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e41dd41..9a535a8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -108,7 +108,6 @@ RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); static struct rcu_state *const rcu_state_p; -static struct rcu_data __percpu *const rcu_data_p; LIST_HEAD(rcu_struct_flavors); /* Dump rcu_node combining tree at boot to verify correct setup. */ @@ -1083,13 +1082,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, rcu_sysidle_check_cpu(rdp, isidle, maxj); if ((rdp->dynticks_snap & 0x1) == 0) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); - return 1; - } else { if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rdp->mynode->gpnum)) WRITE_ONCE(rdp->gpwrap, true); - return 0; + return 1; } + return 0; } /* @@ -1173,15 +1171,16 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, smp_mb(); /* ->cond_resched_completed before *rcrmp. */ WRITE_ONCE(*rcrmp, READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask); - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ - rdp->rsp->jiffies_resched += 5; /* Enable beating. */ - } else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { - /* Time to beat on that CPU again! */ - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ - rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ } + rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ } + /* And if it has been a really long time, kick the CPU as well. */ + if (ULONG_CMP_GE(jiffies, + rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || + ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) + resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + return 0; } @@ -1246,7 +1245,7 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) if (rnp->qsmask & (1UL << cpu)) dump_cpu_task(rnp->grplo + cpu); } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1266,12 +1265,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) raw_spin_lock_irqsave_rcu_node(rnp, flags); delta = jiffies - READ_ONCE(rsp->jiffies_stall); if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* * OK, time to rat on our buddy... @@ -1292,7 +1291,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) ndetected++; } } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } print_cpu_stall_info_end(); @@ -1357,7 +1356,7 @@ static void print_cpu_stall(struct rcu_state *rsp) if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* * Attempt to revive the RCU machinery by forcing a context switch. @@ -1595,7 +1594,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, } unlock_out: if (rnp != rnp_root) - raw_spin_unlock(&rnp_root->lock); + raw_spin_unlock_rcu_node(rnp_root); out: if (c_out != NULL) *c_out = c; @@ -1614,7 +1613,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) int needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - rcu_nocb_gp_cleanup(rsp, rnp); rnp->need_future_gp[c & 0x1] = 0; needmore = rnp->need_future_gp[(c + 1) & 0x1]; trace_rcu_future_gp(rnp, rdp, c, @@ -1635,7 +1633,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - wake_up(&rsp->gp_wq); + swake_up(&rsp->gp_wq); } /* @@ -1815,7 +1813,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) return; } needwake = __note_gp_changes(rsp, rnp, rdp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) rcu_gp_kthread_wake(rsp); } @@ -1840,7 +1838,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) raw_spin_lock_irq_rcu_node(rnp); if (!READ_ONCE(rsp->gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); return false; } WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ @@ -1850,7 +1848,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) * Grace period already in progress, don't start another. * Not supposed to be able to happen. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); return false; } @@ -1859,7 +1857,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* Record GP times before starting GP, hence smp_store_release(). */ smp_store_release(&rsp->gpnum, rsp->gpnum + 1); trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); /* * Apply per-leaf buffered online and offline operations to the @@ -1873,7 +1871,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); continue; } @@ -1907,7 +1905,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) rcu_cleanup_dead_rnp(rnp); } - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); } /* @@ -1938,7 +1936,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) trace_rcu_grace_period_init(rsp->name, rnp->gpnum, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); } @@ -1996,7 +1994,7 @@ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) raw_spin_lock_irq_rcu_node(rnp); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); } } @@ -2010,6 +2008,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); + struct swait_queue_head *sq; WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); @@ -2025,7 +2024,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) * safe for us to drop the lock in order to mark the grace * period as completed in all of the rcu_node structures. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); /* * Propagate new ->completed value to rcu_node structures so @@ -2046,7 +2045,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); - raw_spin_unlock_irq(&rnp->lock); + sq = rcu_nocb_gp_get(rnp); + raw_spin_unlock_irq_rcu_node(rnp); + rcu_nocb_gp_cleanup(sq); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); rcu_gp_slow(rsp, gp_cleanup_delay); @@ -2068,7 +2069,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) READ_ONCE(rsp->gpnum), TPS("newreq")); } - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); } /* @@ -2092,7 +2093,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - wait_event_interruptible(rsp->gp_wq, + swait_event_interruptible(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; @@ -2122,7 +2123,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = wait_event_interruptible_timeout(rsp->gp_wq, + ret = swait_event_interruptible_timeout(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2234,19 +2235,21 @@ static bool rcu_start_gp(struct rcu_state *rsp) } /* - * Report a full set of quiescent states to the specified rcu_state - * data structure. This involves cleaning up after the prior grace - * period and letting rcu_start_gp() start up the next grace period - * if one is needed. Note that the caller must hold rnp->lock, which - * is released before return. + * Report a full set of quiescent states to the specified rcu_state data + * structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period + * kthread if another grace period is required. Whether we wake + * the grace-period kthread or it awakens itself for the next round + * of quiescent-state forcing, that kthread will clean up after the + * just-completed grace period. Note that the caller must hold rnp->lock, + * which is released before return. */ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - rcu_gp_kthread_wake(rsp); + raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ } /* @@ -2275,7 +2278,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * Our bit has already been cleared, or the * relevant grace period is already over, so done. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ @@ -2287,7 +2290,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { /* Other bits still set at this level, so done. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } mask = rnp->grpmask; @@ -2297,7 +2300,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, break; } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); rnp_c = rnp; rnp = rnp->parent; raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -2329,7 +2332,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; /* Still need more quiescent states! */ } @@ -2346,19 +2349,14 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, /* Report up the rest of the hierarchy, tracking current ->gpnum. */ gps = rnp->gpnum; mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); } /* * Record a quiescent state for the specified CPU to that CPU's rcu_data - * structure. This must be either called from the specified CPU, or - * called when the specified CPU is known to be offline (and when it is - * also known that no other CPU is concurrently trying to help the offline - * CPU). The lastcomp argument is used to make sure we are still in the - * grace period of interest. We don't want to end the current grace period - * based on quiescent states detected in an earlier grace period! + * structure. This must be called from the specified CPU. */ static void rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) @@ -2383,14 +2381,14 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) */ rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } mask = rdp->grpmask; if ((rnp->qsmask & mask) == 0) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } else { - rdp->core_needs_qs = 0; + rdp->core_needs_qs = false; /* * This GP can't end until cpu checks in, so all of our @@ -2599,36 +2597,15 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) rnp->qsmaskinit &= ~mask; rnp->qsmask &= ~mask; if (rnp->qsmaskinit) { - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); + /* irqs remain disabled. */ return; } - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ } } /* - * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit - * bit masks. - */ -static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) -{ - unsigned long flags; - unsigned long mask; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; - - /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ - mask = rdp->grpmask; - raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ - rnp->qsmaskinitnext &= ~mask; - raw_spin_unlock_irqrestore(&rnp->lock, flags); -} - -/* * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, * including orphaning the outgoing CPU's RCU callbacks, and also @@ -2859,7 +2836,7 @@ static void force_qs_rnp(struct rcu_state *rsp, rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); } else { /* Nothing to do here, so just drop the lock. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } } @@ -2895,12 +2872,12 @@ static void force_quiescent_state(struct rcu_state *rsp) raw_spin_unlock(&rnp_old->fqslock); if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { rsp->n_force_qs_lh++; - raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); return; /* Someone beat us to it. */ } WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - rcu_gp_kthread_wake(rsp); + raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ } /* @@ -2925,7 +2902,7 @@ __rcu_process_callbacks(struct rcu_state *rsp) if (cpu_needs_another_gp(rsp, rdp)) { raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */ needwake = rcu_start_gp(rsp); - raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); if (needwake) rcu_gp_kthread_wake(rsp); } else { @@ -3016,7 +2993,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, raw_spin_lock_rcu_node(rnp_root); needwake = rcu_start_gp(rsp); - raw_spin_unlock(&rnp_root->lock); + raw_spin_unlock_rcu_node(rnp_root); if (needwake) rcu_gp_kthread_wake(rsp); } else { @@ -3436,14 +3413,14 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmaskinit == rnp->expmaskinitnext) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); continue; /* No new CPUs, nothing to do. */ } /* Update this node's mask, track old value for propagation. */ oldmask = rnp->expmaskinit; rnp->expmaskinit = rnp->expmaskinitnext; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* If was already nonzero, nothing to propagate. */ if (oldmask) @@ -3458,7 +3435,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) if (rnp_up->expmaskinit) done = true; rnp_up->expmaskinit |= mask; - raw_spin_unlock_irqrestore(&rnp_up->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp_up, flags); if (done) break; mask = rnp_up->grpmask; @@ -3481,7 +3458,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) raw_spin_lock_irqsave_rcu_node(rnp, flags); WARN_ON_ONCE(rnp->expmask); rnp->expmask = rnp->expmaskinit; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -3522,19 +3499,19 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, if (!rnp->expmask) rcu_initiate_boost(rnp, flags); else - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); break; } if (rnp->parent == NULL) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - wake_up(&rsp->expedited_wq); + swake_up(&rsp->expedited_wq); } break; } mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled */ rnp = rnp->parent; raw_spin_lock_rcu_node(rnp); /* irqs already disabled */ WARN_ON_ONCE(!(rnp->expmask & mask)); @@ -3569,7 +3546,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!(rnp->expmask & mask)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } rnp->expmask &= ~mask; @@ -3730,7 +3707,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, */ if (rcu_preempt_has_tasks(rnp)) rnp->exp_tasks = rnp->blkd_tasks.next; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* IPI the remaining CPUs for expedited quiescent state. */ mask = 1; @@ -3747,7 +3724,7 @@ retry_ipi: raw_spin_lock_irqsave_rcu_node(rnp, flags); if (cpu_online(cpu) && (rnp->expmask & mask)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); schedule_timeout_uninterruptible(1); if (cpu_online(cpu) && (rnp->expmask & mask)) @@ -3756,7 +3733,7 @@ retry_ipi: } if (!(rnp->expmask & mask)) mask_ofl_ipi &= ~mask; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; @@ -3780,7 +3757,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = wait_event_interruptible_timeout( + ret = swait_event_timeout( rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); @@ -3788,7 +3765,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ - wait_event(rsp->expedited_wq, + swait_event(rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root)); return; } @@ -4163,7 +4140,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) return; raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ rnp->qsmaskinit |= mask; - raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */ } } @@ -4187,7 +4164,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->rsp = rsp; mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* @@ -4215,7 +4192,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rcu_sysidle_init_percpu_data(rdp->dynticks); atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ /* * Add CPU to leaf rcu_node pending-online bitmask. Any needed @@ -4236,7 +4213,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); rdp->core_needs_qs = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } static void rcu_prepare_cpu(int cpu) @@ -4247,6 +4224,46 @@ static void rcu_prepare_cpu(int cpu) rcu_init_percpu_data(cpu, rsp); } +#ifdef CONFIG_HOTPLUG_CPU +/* + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + */ +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return; + + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ + mask = rdp->grpmask; + raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ + rnp->qsmaskinitnext &= ~mask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +void rcu_report_dead(unsigned int cpu) +{ + struct rcu_state *rsp; + + /* QS for any half-done expedited RCU-sched GP. */ + preempt_disable(); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(rcu_sched_state.rda), true); + preempt_enable(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_idle_cpu(cpu, rsp); +} +#endif + /* * Handle CPU online/offline notification events. */ @@ -4278,17 +4295,6 @@ int rcu_cpu_notify(struct notifier_block *self, for_each_rcu_flavor(rsp) rcu_cleanup_dying_cpu(rsp); break; - case CPU_DYING_IDLE: - /* QS for any half-done expedited RCU-sched GP. */ - preempt_disable(); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(rcu_sched_state.rda), true); - preempt_enable(); - - for_each_rcu_flavor(rsp) { - rcu_cleanup_dying_idle_cpu(cpu, rsp); - } - break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: @@ -4358,7 +4364,7 @@ static int __init rcu_spawn_gp_kthread(void) sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); wake_up_process(t); } rcu_spawn_nocb_kthreads(); @@ -4449,8 +4455,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) cpustride *= levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < levelcnt[i]; j++, rnp++) { - raw_spin_lock_init(&rnp->lock); - lockdep_set_class_and_name(&rnp->lock, + raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock)); + lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock), &rcu_node_class[i], buf[i]); raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, @@ -4482,8 +4488,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) } } - init_waitqueue_head(&rsp->gp_wq); - init_waitqueue_head(&rsp->expedited_wq); + init_swait_queue_head(&rsp->gp_wq); + init_swait_queue_head(&rsp->expedited_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 83360b4..df668c0 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -27,6 +27,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/seqlock.h> +#include <linux/swait.h> #include <linux/stop_machine.h> /* @@ -149,8 +150,9 @@ struct rcu_dynticks { * Definition for node within the RCU grace-period-detection hierarchy. */ struct rcu_node { - raw_spinlock_t lock; /* Root rcu_node's lock protects some */ - /* rcu_state fields as well as following. */ + raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ + /* some rcu_state fields as well as */ + /* following. */ unsigned long gpnum; /* Current grace period for this node. */ /* This will either be equal to or one */ /* behind the root rcu_node's gpnum. */ @@ -243,7 +245,7 @@ struct rcu_node { /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ #ifdef CONFIG_RCU_NOCB_CPU - wait_queue_head_t nocb_gp_wq[2]; + struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ int need_future_gp[2]; @@ -399,7 +401,7 @@ struct rcu_data { atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ struct rcu_head **nocb_follower_tail; - wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ + struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ @@ -478,7 +480,7 @@ struct rcu_state { unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ - wait_queue_head_t gp_wq; /* Where GP task waits. */ + struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ short gp_state; /* GP kthread sleep state. */ @@ -506,7 +508,7 @@ struct rcu_state { unsigned long expedited_sequence; /* Take a ticket. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ - wait_queue_head_t expedited_wq; /* Wait for check-ins. */ + struct swait_queue_head expedited_wq; /* Wait for check-ins. */ int ncpus_snap; /* # CPUs seen last time. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ @@ -621,7 +623,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags); @@ -680,7 +683,7 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #endif /* #else #ifdef CONFIG_PPC */ /* - * Wrappers for the rcu_node::lock acquire. + * Wrappers for the rcu_node::lock acquire and release. * * Because the rcu_nodes form a tree, the tree traversal locking will observe * different lock values, this in turn means that an UNLOCK of one level @@ -689,29 +692,48 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) * * In order to restore full ordering between tree levels, augment the regular * lock acquire functions with smp_mb__after_unlock_lock(). + * + * As ->lock of struct rcu_node is a __private field, therefore one should use + * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock. */ static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp) { - raw_spin_lock(&rnp->lock); + raw_spin_lock(&ACCESS_PRIVATE(rnp, lock)); smp_mb__after_unlock_lock(); } +static inline void raw_spin_unlock_rcu_node(struct rcu_node *rnp) +{ + raw_spin_unlock(&ACCESS_PRIVATE(rnp, lock)); +} + static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp) { - raw_spin_lock_irq(&rnp->lock); + raw_spin_lock_irq(&ACCESS_PRIVATE(rnp, lock)); smp_mb__after_unlock_lock(); } -#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ -do { \ - typecheck(unsigned long, flags); \ - raw_spin_lock_irqsave(&(rnp)->lock, flags); \ - smp_mb__after_unlock_lock(); \ +static inline void raw_spin_unlock_irq_rcu_node(struct rcu_node *rnp) +{ + raw_spin_unlock_irq(&ACCESS_PRIVATE(rnp, lock)); +} + +#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ +do { \ + typecheck(unsigned long, flags); \ + raw_spin_lock_irqsave(&ACCESS_PRIVATE(rnp, lock), flags); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_irqrestore_rcu_node(rnp, flags) \ +do { \ + typecheck(unsigned long, flags); \ + raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(rnp, lock), flags); \ } while (0) static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp) { - bool locked = raw_spin_trylock(&rnp->lock); + bool locked = raw_spin_trylock(&ACCESS_PRIVATE(rnp, lock)); if (locked) smp_mb__after_unlock_lock(); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 9467a8b..efdf7b6 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -235,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) rnp->gp_tasks = &t->rcu_node_entry; if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; - raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* interrupts remain disabled. */ /* * Report the quiescent state for the expedited GP. This expedited @@ -489,7 +489,7 @@ void rcu_read_unlock_special(struct task_struct *t) !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags); } else { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Unboost if we were boosted. */ @@ -518,14 +518,14 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!rcu_preempt_blocked_readers_cgp(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) sched_show_task(t); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* @@ -807,7 +807,6 @@ void exit_rcu(void) #else /* #ifdef CONFIG_PREEMPT_RCU */ static struct rcu_state *const rcu_state_p = &rcu_sched_state; -static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data; /* * Tell them what RCU they are running. @@ -991,7 +990,7 @@ static int rcu_boost(struct rcu_node *rnp) * might exit their RCU read-side critical sections on their own. */ if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return 0; } @@ -1028,7 +1027,7 @@ static int rcu_boost(struct rcu_node *rnp) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* Lock only for side effect: boosts task t's priority. */ rt_mutex_lock(&rnp->boost_mtx); rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */ @@ -1088,7 +1087,7 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { rnp->n_balk_exp_gp_tasks++; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } if (rnp->exp_tasks != NULL || @@ -1098,13 +1097,13 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) ULONG_CMP_GE(jiffies, rnp->boost_time))) { if (rnp->exp_tasks == NULL) rnp->boost_tasks = rnp->gp_tasks; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); t = rnp->boost_kthread_task; if (t) rcu_wake_cond(t, rnp->boost_kthread_status); } else { rcu_initiate_boost_trace(rnp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1172,7 +1171,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, return PTR_ERR(t); raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ @@ -1308,7 +1307,7 @@ static void rcu_prepare_kthreads(int cpu) static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } static void invoke_rcu_callbacks_kthread(void) @@ -1559,7 +1558,7 @@ static void rcu_prepare_for_idle(void) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ if (needwake) rcu_gp_kthread_wake(rsp); } @@ -1811,9 +1810,9 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll); * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended * grace period. */ -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + swake_up_all(sq); } /* @@ -1829,10 +1828,15 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return &rnp->nocb_gp_wq[rnp->completed & 0x1]; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { - init_waitqueue_head(&rnp->nocb_gp_wq[0]); - init_waitqueue_head(&rnp->nocb_gp_wq[1]); + init_swait_queue_head(&rnp->nocb_gp_wq[0]); + init_swait_queue_head(&rnp->nocb_gp_wq[1]); } #ifndef CONFIG_RCU_NOCB_CPU_ALL @@ -1857,7 +1861,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); - wake_up(&rdp_leader->nocb_wq); + swake_up(&rdp_leader->nocb_wq); } } @@ -2059,7 +2063,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) raw_spin_lock_irqsave_rcu_node(rnp, flags); needwake = rcu_start_future_gp(rnp, rdp, &c); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) rcu_gp_kthread_wake(rdp->rsp); @@ -2069,7 +2073,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - wait_event_interruptible( + swait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); if (likely(d)) @@ -2097,7 +2101,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); - wait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); /* Memory barrier handled by smp_mb() calls below and repoll. */ } else if (firsttime) { @@ -2172,7 +2176,7 @@ wait_again: * List was empty, wake up the follower. * Memory barriers supplied by atomic_long_add(). */ - wake_up(&rdp->nocb_wq); + swake_up(&rdp->nocb_wq); } } @@ -2193,7 +2197,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) if (!rcu_nocb_poll) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "FollowerSleep"); - wait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); } else if (firsttime) { /* Don't drown trace log with "Poll"! */ @@ -2352,7 +2356,7 @@ void __init rcu_init_nohz(void) static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { rdp->nocb_tail = &rdp->nocb_head; - init_waitqueue_head(&rdp->nocb_wq); + init_swait_queue_head(&rdp->nocb_wq); rdp->nocb_follower_tail = &rdp->nocb_follower_head; } @@ -2502,7 +2506,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) return false; } -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { } @@ -2510,6 +2514,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) { } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return NULL; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { } diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 76b94e1..ca828b4 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -128,6 +128,7 @@ bool rcu_gp_is_normal(void) { return READ_ONCE(rcu_normal); } +EXPORT_SYMBOL_GPL(rcu_gp_is_normal); static atomic_t rcu_expedited_nesting = ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); diff --git a/kernel/resource.c b/kernel/resource.c index 3669d1b..4d46605 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -333,13 +333,13 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /* - * Finds the lowest iomem reosurce exists with-in [res->start.res->end) - * the caller must specify res->start, res->end, res->flags and "name". - * If found, returns 0, res is overwritten, if not found, returns -1. - * This walks through whole tree and not just first level children - * until and unless first_level_children_only is true. + * Finds the lowest iomem resource existing within [res->start.res->end). + * The caller must specify res->start, res->end, res->flags, and optionally + * desc. If found, returns 0, res is overwritten, if not found, returns -1. + * This function walks the whole tree and not just first level children until + * and unless first_level_children_only is true. */ -static int find_next_iomem_res(struct resource *res, char *name, +static int find_next_iomem_res(struct resource *res, unsigned long desc, bool first_level_children_only) { resource_size_t start, end; @@ -358,9 +358,9 @@ static int find_next_iomem_res(struct resource *res, char *name, read_lock(&resource_lock); for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) { - if (p->flags != res->flags) + if ((p->flags & res->flags) != res->flags) continue; - if (name && strcmp(p->name, name)) + if ((desc != IORES_DESC_NONE) && (desc != p->desc)) continue; if (p->start > end) { p = NULL; @@ -385,15 +385,18 @@ static int find_next_iomem_res(struct resource *res, char *name, * Walks through iomem resources and calls func() with matching resource * ranges. This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and - * name are valid candidates. + * desc are valid candidates. * - * @name: name of resource - * @flags: resource flags + * @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check. + * @flags: I/O resource flags * @start: start addr * @end: end addr + * + * NOTE: For a new descriptor search, define a new IORES_DESC in + * <linux/ioport.h> and set it in 'desc' of a target resource entry. */ -int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, - void *arg, int (*func)(u64, u64, void *)) +int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, + u64 end, void *arg, int (*func)(u64, u64, void *)) { struct resource res; u64 orig_end; @@ -403,23 +406,27 @@ int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, res.end = end; res.flags = flags; orig_end = res.end; + while ((res.start < res.end) && - (!find_next_iomem_res(&res, name, false))) { + (!find_next_iomem_res(&res, desc, false))) { + ret = (*func)(res.start, res.end, arg); if (ret) break; + res.start = res.end + 1; res.end = orig_end; } + return ret; } /* - * This function calls callback against all memory range of "System RAM" - * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. - * Now, this function is only for "System RAM". This function deals with - * full ranges and not pfn. If resources are not pfn aligned, dealing - * with pfn can truncate ranges. + * This function calls the @func callback against all memory ranges of type + * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. + * Now, this function is only for System RAM, it deals with full ranges and + * not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate + * ranges. */ int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(u64, u64, void *)) @@ -430,10 +437,10 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, res.start = start; res.end = end; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; orig_end = res.end; while ((res.start < res.end) && - (!find_next_iomem_res(&res, "System RAM", true))) { + (!find_next_iomem_res(&res, IORES_DESC_NONE, true))) { ret = (*func)(res.start, res.end, arg); if (ret) break; @@ -446,9 +453,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) /* - * This function calls callback against all memory range of "System RAM" - * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. - * Now, this function is only for "System RAM". + * This function calls the @func callback against all memory ranges of type + * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. + * It is to be used only for System RAM. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) @@ -460,10 +467,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, res.start = (u64) start_pfn << PAGE_SHIFT; res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; orig_end = res.end; while ((res.start < res.end) && - (find_next_iomem_res(&res, "System RAM", true) >= 0)) { + (find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) { pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; end_pfn = (res.end + 1) >> PAGE_SHIFT; if (end_pfn > pfn) @@ -484,7 +491,7 @@ static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) } /* * This generic page_is_ram() returns true if specified address is - * registered as "System RAM" in iomem_resource list. + * registered as System RAM in iomem_resource list. */ int __weak page_is_ram(unsigned long pfn) { @@ -496,30 +503,34 @@ EXPORT_SYMBOL_GPL(page_is_ram); * region_intersects() - determine intersection of region with known resources * @start: region start address * @size: size of region - * @name: name of resource (in iomem_resource) + * @flags: flags of resource (in iomem_resource) + * @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE * * Check if the specified region partially overlaps or fully eclipses a - * resource identified by @name. Return REGION_DISJOINT if the region - * does not overlap @name, return REGION_MIXED if the region overlaps - * @type and another resource, and return REGION_INTERSECTS if the - * region overlaps @type and no other defined resource. Note, that - * REGION_INTERSECTS is also returned in the case when the specified - * region overlaps RAM and undefined memory holes. + * resource identified by @flags and @desc (optional with IORES_DESC_NONE). + * Return REGION_DISJOINT if the region does not overlap @flags/@desc, + * return REGION_MIXED if the region overlaps @flags/@desc and another + * resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc + * and no other defined resource. Note that REGION_INTERSECTS is also + * returned in the case when the specified region overlaps RAM and undefined + * memory holes. * * region_intersect() is used by memory remapping functions to ensure * the user is not remapping RAM and is a vast speed up over walking * through the resource table page by page. */ -int region_intersects(resource_size_t start, size_t size, const char *name) +int region_intersects(resource_size_t start, size_t size, unsigned long flags, + unsigned long desc) { - unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; resource_size_t end = start + size - 1; int type = 0; int other = 0; struct resource *p; read_lock(&resource_lock); for (p = iomem_resource.child; p ; p = p->sibling) { - bool is_type = strcmp(p->name, name) == 0 && p->flags == flags; + bool is_type = (((p->flags & flags) == flags) && + ((desc == IORES_DESC_NONE) || + (desc == p->desc))); if (start >= p->start && start <= p->end) is_type ? type++ : other++; @@ -538,6 +549,7 @@ int region_intersects(resource_size_t start, size_t size, const char *name) return REGION_DISJOINT; } +EXPORT_SYMBOL_GPL(region_intersects); void __weak arch_remove_reservations(struct resource *avail) { @@ -948,6 +960,7 @@ static void __init __reserve_region_with_split(struct resource *root, res->start = start; res->end = end; res->flags = IORESOURCE_BUSY; + res->desc = IORES_DESC_NONE; while (1) { @@ -982,6 +995,7 @@ static void __init __reserve_region_with_split(struct resource *root, next_res->start = conflict->end + 1; next_res->end = end; next_res->flags = IORESOURCE_BUSY; + next_res->desc = IORES_DESC_NONE; } } else { res->start = conflict->end + 1; @@ -1071,8 +1085,9 @@ struct resource * __request_region(struct resource *parent, res->name = name; res->start = start; res->end = start + n - 1; - res->flags = resource_type(parent); + res->flags = resource_type(parent) | resource_ext_type(parent); res->flags |= IORESOURCE_BUSY | flags; + res->desc = IORES_DESC_NONE; write_lock(&resource_lock); @@ -1238,6 +1253,7 @@ int release_mem_region_adjustable(struct resource *parent, new_res->start = end + 1; new_res->end = res->end; new_res->flags = res->flags; + new_res->desc = res->desc; new_res->parent = res->parent; new_res->sibling = res->sibling; new_res->child = NULL; @@ -1413,6 +1429,7 @@ static int __init reserve_setup(char *str) res->start = io_start; res->end = io_start + io_num - 1; res->flags = IORESOURCE_BUSY; + res->desc = IORES_DESC_NONE; res->child = NULL; if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0) reserved = x+1; diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 6768797..7d4cba2 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -13,7 +13,7 @@ endif obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o completion.o idle.o +obj-y += wait.o swait.o completion.o idle.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index bc54e84..fedb967 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -61,6 +61,7 @@ #include <linux/static_key.h> #include <linux/workqueue.h> #include <linux/compiler.h> +#include <linux/tick.h> /* * Scheduler clock - returns current time in nanosec units. @@ -89,6 +90,8 @@ static void __set_sched_clock_stable(void) { if (!sched_clock_stable()) static_key_slow_inc(&__sched_clock_stable); + + tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } void set_sched_clock_stable(void) @@ -108,6 +111,8 @@ static void __clear_sched_clock_stable(struct work_struct *work) /* XXX worry about clock continuity */ if (sched_clock_stable()) static_key_slow_dec(&__sched_clock_stable); + + tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); } static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 406182a..4d872e1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,6 +26,7 @@ * Thomas Gleixner, Mike Kravetz */ +#include <linux/kasan.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nmi.h> @@ -66,12 +67,10 @@ #include <linux/pagemap.h> #include <linux/hrtimer.h> #include <linux/tick.h> -#include <linux/debugfs.h> #include <linux/ctype.h> #include <linux/ftrace.h> #include <linux/slab.h> #include <linux/init_task.h> -#include <linux/binfmts.h> #include <linux/context_tracking.h> #include <linux/compiler.h> @@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features = #undef SCHED_FEAT -#ifdef CONFIG_SCHED_DEBUG -#define SCHED_FEAT(name, enabled) \ - #name , - -static const char * const sched_feat_names[] = { -#include "features.h" -}; - -#undef SCHED_FEAT - -static int sched_feat_show(struct seq_file *m, void *v) -{ - int i; - - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (!(sysctl_sched_features & (1UL << i))) - seq_puts(m, "NO_"); - seq_printf(m, "%s ", sched_feat_names[i]); - } - seq_puts(m, "\n"); - - return 0; -} - -#ifdef HAVE_JUMP_LABEL - -#define jump_label_key__true STATIC_KEY_INIT_TRUE -#define jump_label_key__false STATIC_KEY_INIT_FALSE - -#define SCHED_FEAT(name, enabled) \ - jump_label_key__##enabled , - -struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { -#include "features.h" -}; - -#undef SCHED_FEAT - -static void sched_feat_disable(int i) -{ - static_key_disable(&sched_feat_keys[i]); -} - -static void sched_feat_enable(int i) -{ - static_key_enable(&sched_feat_keys[i]); -} -#else -static void sched_feat_disable(int i) { }; -static void sched_feat_enable(int i) { }; -#endif /* HAVE_JUMP_LABEL */ - -static int sched_feat_set(char *cmp) -{ - int i; - int neg = 0; - - if (strncmp(cmp, "NO_", 3) == 0) { - neg = 1; - cmp += 3; - } - - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (strcmp(cmp, sched_feat_names[i]) == 0) { - if (neg) { - sysctl_sched_features &= ~(1UL << i); - sched_feat_disable(i); - } else { - sysctl_sched_features |= (1UL << i); - sched_feat_enable(i); - } - break; - } - } - - return i; -} - -static ssize_t -sched_feat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - char *cmp; - int i; - struct inode *inode; - - if (cnt > 63) - cnt = 63; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); - - /* Ensure the static_key remains in a consistent state */ - inode = file_inode(filp); - inode_lock(inode); - i = sched_feat_set(cmp); - inode_unlock(inode); - if (i == __SCHED_FEAT_NR) - return -EINVAL; - - *ppos += cnt; - - return cnt; -} - -static int sched_feat_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, sched_feat_show, NULL); -} - -static const struct file_operations sched_feat_fops = { - .open = sched_feat_open, - .write = sched_feat_write, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static __init int sched_init_debug(void) -{ - debugfs_create_file("sched_features", 0644, NULL, NULL, - &sched_feat_fops); - - return 0; -} -late_initcall(sched_init_debug); -#endif /* CONFIG_SCHED_DEBUG */ - /* * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. @@ -453,20 +320,6 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ -/* - * cmpxchg based fetch_or, macro so it works for different integer types - */ -#define fetch_or(ptr, val) \ -({ typeof(*(ptr)) __old, __val = *(ptr); \ - for (;;) { \ - __old = cmpxchg((ptr), __val, __val | (val)); \ - if (__old == __val) \ - break; \ - __val = __old; \ - } \ - __old; \ -}) - #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, @@ -715,31 +568,36 @@ static inline bool got_nohz_idle_kick(void) #endif /* CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL -bool sched_can_stop_tick(void) +bool sched_can_stop_tick(struct rq *rq) { + int fifo_nr_running; + + /* Deadline tasks, even if single, need the tick */ + if (rq->dl.dl_nr_running) + return false; + /* - * FIFO realtime policy runs the highest priority task. Other runnable - * tasks are of a lower priority. The scheduler tick does nothing. + * FIFO realtime policy runs the highest priority task (after DEADLINE). + * Other runnable tasks are of a lower priority. The scheduler tick + * isn't needed. */ - if (current->policy == SCHED_FIFO) + fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; + if (fifo_nr_running) return true; /* * Round-robin realtime tasks time slice with other tasks at the same - * realtime priority. Is this task the only one at this priority? + * realtime priority. */ - if (current->policy == SCHED_RR) { - struct sched_rt_entity *rt_se = ¤t->rt; - - return list_is_singular(&rt_se->run_list); + if (rq->rt.rr_nr_running) { + if (rq->rt.rr_nr_running == 1) + return true; + else + return false; } - /* - * More than one running task need preemption. - * nr_running update is assumed to be visible - * after IPI is sent from wakers. - */ - if (this_rq()->nr_running > 1) + /* Normal multitasking need periodic preemption checks */ + if (rq->cfs.nr_running > 1) return false; return true; @@ -2093,7 +1951,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) ttwu_queue(p, cpu); stat: - ttwu_stat(p, cpu, wake_flags); + if (schedstat_enabled()) + ttwu_stat(p, cpu, wake_flags); out: raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2141,7 +2000,8 @@ static void try_to_wake_up_local(struct task_struct *p) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_do_wakeup(rq, p, 0); - ttwu_stat(p, smp_processor_id(), 0); + if (schedstat_enabled()) + ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); } @@ -2183,7 +2043,6 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_throttled = 0; - dl_se->dl_new = 1; dl_se->dl_yielded = 0; } @@ -2210,6 +2069,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #endif #ifdef CONFIG_SCHEDSTATS + /* Even if schedstat is disabled, there should not be garbage */ memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif @@ -2218,6 +2078,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); + p->rt.timeout = 0; + p->rt.time_slice = sched_rr_timeslice; + p->rt.on_rq = 0; + p->rt.on_list = 0; #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2281,6 +2145,69 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #endif #endif +DEFINE_STATIC_KEY_FALSE(sched_schedstats); + +#ifdef CONFIG_SCHEDSTATS +static void set_schedstats(bool enabled) +{ + if (enabled) + static_branch_enable(&sched_schedstats); + else + static_branch_disable(&sched_schedstats); +} + +void force_schedstat_enabled(void) +{ + if (!schedstat_enabled()) { + pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n"); + static_branch_enable(&sched_schedstats); + } +} + +static int __init setup_schedstats(char *str) +{ + int ret = 0; + if (!str) + goto out; + + if (!strcmp(str, "enable")) { + set_schedstats(true); + ret = 1; + } else if (!strcmp(str, "disable")) { + set_schedstats(false); + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse schedstats=\n"); + + return ret; +} +__setup("schedstats=", setup_schedstats); + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_schedstats(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_schedstats); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_schedstats(state); + return err; +} +#endif +#endif + /* * fork()/clone()-time setup: */ @@ -3010,16 +2937,6 @@ u64 scheduler_tick_max_deferment(void) } #endif -notrace unsigned long get_parent_ip(unsigned long addr) -{ - if (in_lock_functions(addr)) { - addr = CALLER_ADDR2; - if (in_lock_functions(addr)) - addr = CALLER_ADDR3; - } - return addr; -} - #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) @@ -3041,7 +2958,7 @@ void preempt_count_add(int val) PREEMPT_MASK - 10); #endif if (preempt_count() == val) { - unsigned long ip = get_parent_ip(CALLER_ADDR1); + unsigned long ip = get_lock_parent_ip(); #ifdef CONFIG_DEBUG_PREEMPT current->preempt_disable_ip = ip; #endif @@ -3068,7 +2985,7 @@ void preempt_count_sub(int val) #endif if (preempt_count() == val) - trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); @@ -3280,7 +3197,6 @@ static void __sched notrace __schedule(bool preempt) trace_sched_switch(preempt, prev, next); rq = context_switch(rq, prev, next); /* unlocks the rq */ - cpu = cpu_of(rq); } else { lockdep_unpin_lock(&rq->lock); raw_spin_unlock_irq(&rq->lock); @@ -3466,7 +3382,7 @@ EXPORT_SYMBOL(default_wake_function); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE; + int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE; struct rq *rq; const struct sched_class *prev_class; @@ -3494,11 +3410,15 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; + + if (oldprio == prio) + queue_flag &= ~DEQUEUE_MOVE; + prev_class = p->sched_class; queued = task_on_rq_queued(p); running = task_current(rq, p); if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); + dequeue_task(rq, p, queue_flag); if (running) put_prev_task(rq, p); @@ -3516,7 +3436,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (!dl_prio(p->normal_prio) || (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; - enqueue_flag |= ENQUEUE_REPLENISH; + queue_flag |= ENQUEUE_REPLENISH; } else p->dl.dl_boosted = 0; p->sched_class = &dl_sched_class; @@ -3524,7 +3444,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (dl_prio(oldprio)) p->dl.dl_boosted = 0; if (oldprio < prio) - enqueue_flag |= ENQUEUE_HEAD; + queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) @@ -3539,7 +3459,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); if (queued) - enqueue_task(rq, p, enqueue_flag); + enqueue_task(rq, p, queue_flag); check_class_changed(rq, p, prev_class, oldprio); out_unlock: @@ -3895,6 +3815,7 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_class *prev_class; struct rq *rq; int reset_on_fork; + int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -4077,17 +3998,14 @@ change: * itself. */ new_effective_prio = rt_mutex_get_effective_prio(p, newprio); - if (new_effective_prio == oldprio) { - __setscheduler_params(p, attr); - task_rq_unlock(rq, p, &flags); - return 0; - } + if (new_effective_prio == oldprio) + queue_flags &= ~DEQUEUE_MOVE; } queued = task_on_rq_queued(p); running = task_current(rq, p); if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); + dequeue_task(rq, p, queue_flags); if (running) put_prev_task(rq, p); @@ -4097,15 +4015,14 @@ change: if (running) p->sched_class->set_curr_task(rq); if (queued) { - int enqueue_flags = ENQUEUE_RESTORE; /* * We enqueue to tail when the priority of a task is * increased (user space view). */ - if (oldprio <= p->prio) - enqueue_flags |= ENQUEUE_HEAD; + if (oldprio < p->prio) + queue_flags |= ENQUEUE_HEAD; - enqueue_task(rq, p, enqueue_flags); + enqueue_task(rq, p, queue_flags); } check_class_changed(rq, p, prev_class, oldprio); @@ -5096,6 +5013,8 @@ void init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); + kasan_unpoison_task_stack(idle); + #ifdef CONFIG_SMP /* * Its possible that init_idle() gets called multiple times on a task, @@ -5405,183 +5324,6 @@ static void migrate_tasks(struct rq *dead_rq) } #endif /* CONFIG_HOTPLUG_CPU */ -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) - -static struct ctl_table sd_ctl_dir[] = { - { - .procname = "sched_domain", - .mode = 0555, - }, - {} -}; - -static struct ctl_table sd_ctl_root[] = { - { - .procname = "kernel", - .mode = 0555, - .child = sd_ctl_dir, - }, - {} -}; - -static struct ctl_table *sd_alloc_ctl_entry(int n) -{ - struct ctl_table *entry = - kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); - - return entry; -} - -static void sd_free_ctl_entry(struct ctl_table **tablep) -{ - struct ctl_table *entry; - - /* - * In the intermediate directories, both the child directory and - * procname are dynamically allocated and could fail but the mode - * will always be set. In the lowest directory the names are - * static strings and all have proc handlers. - */ - for (entry = *tablep; entry->mode; entry++) { - if (entry->child) - sd_free_ctl_entry(&entry->child); - if (entry->proc_handler == NULL) - kfree(entry->procname); - } - - kfree(*tablep); - *tablep = NULL; -} - -static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX-1; - -static void -set_table_entry(struct ctl_table *entry, - const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler, - bool load_idx) -{ - entry->procname = procname; - entry->data = data; - entry->maxlen = maxlen; - entry->mode = mode; - entry->proc_handler = proc_handler; - - if (load_idx) { - entry->extra1 = &min_load_idx; - entry->extra2 = &max_load_idx; - } -} - -static struct ctl_table * -sd_alloc_ctl_domain_table(struct sched_domain *sd) -{ - struct ctl_table *table = sd_alloc_ctl_entry(14); - - if (table == NULL) - return NULL; - - set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[9], "cache_nice_tries", - &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "max_newidle_lb_cost", - &sd->max_newidle_lb_cost, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[12], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[13] is terminator */ - - return table; -} - -static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) -{ - struct ctl_table *entry, *table; - struct sched_domain *sd; - int domain_num = 0, i; - char buf[32]; - - for_each_domain(cpu, sd) - domain_num++; - entry = table = sd_alloc_ctl_entry(domain_num + 1); - if (table == NULL) - return NULL; - - i = 0; - for_each_domain(cpu, sd) { - snprintf(buf, 32, "domain%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_domain_table(sd); - entry++; - i++; - } - return table; -} - -static struct ctl_table_header *sd_sysctl_header; -static void register_sched_domain_sysctl(void) -{ - int i, cpu_num = num_possible_cpus(); - struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); - char buf[32]; - - WARN_ON(sd_ctl_dir[0].child); - sd_ctl_dir[0].child = entry; - - if (entry == NULL) - return; - - for_each_possible_cpu(i) { - snprintf(buf, 32, "cpu%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_cpu_table(i); - entry++; - } - - WARN_ON(sd_sysctl_header); - sd_sysctl_header = register_sysctl_table(sd_ctl_root); -} - -/* may be called multiple times per register */ -static void unregister_sched_domain_sysctl(void) -{ - unregister_sysctl_table(sd_sysctl_header); - sd_sysctl_header = NULL; - if (sd_ctl_dir[0].child) - sd_free_ctl_entry(&sd_ctl_dir[0].child); -} -#else -static void register_sched_domain_sysctl(void) -{ -} -static void unregister_sched_domain_sysctl(void) -{ -} -#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */ - static void set_rq_online(struct rq *rq) { if (!rq->online) { @@ -5693,16 +5435,6 @@ static int sched_cpu_active(struct notifier_block *nfb, set_cpu_rq_start_time(); return NOTIFY_OK; - case CPU_ONLINE: - /* - * At this point a starting CPU has marked itself as online via - * set_cpu_online(). But it might not yet have marked itself - * as active, which is essential from here on. - */ - set_cpu_active(cpu, true); - stop_machine_unpark(cpu); - return NOTIFY_OK; - case CPU_DOWN_FAILED: set_cpu_active(cpu, true); return NOTIFY_OK; @@ -6174,11 +5906,16 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + int ret; + alloc_bootmem_cpumask_var(&cpu_isolated_map); - cpulist_parse(str, cpu_isolated_map); + ret = cpulist_parse(str, cpu_isolated_map); + if (ret) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); + return 0; + } return 1; } - __setup("isolcpus=", isolated_cpu_setup); struct s_data { @@ -7889,7 +7626,7 @@ void sched_move_task(struct task_struct *tsk) queued = task_on_rq_queued(tsk); if (queued) - dequeue_task(rq, tsk, DEQUEUE_SAVE); + dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE); if (unlikely(running)) put_prev_task(rq, tsk); @@ -7913,7 +7650,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->set_curr_task(rq); if (queued) - enqueue_task(rq, tsk, ENQUEUE_RESTORE); + enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); task_rq_unlock(rq, tsk, &flags); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b2ab2ff..75f98c5 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -262,21 +262,21 @@ static __always_inline bool steal_account_process_tick(void) #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { u64 steal; - cputime_t steal_ct; + unsigned long steal_jiffies; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; /* - * cputime_t may be less precise than nsecs (eg: if it's - * based on jiffies). Lets cast the result to cputime + * steal is in nsecs but our caller is expecting steal + * time in jiffies. Lets cast the result to jiffies * granularity and account the rest on the next rounds. */ - steal_ct = nsecs_to_cputime(steal); - this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + steal_jiffies = nsecs_to_jiffies(steal); + this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies); - account_steal_time(steal_ct); - return steal_ct; + account_steal_time(jiffies_to_cputime(steal_jiffies)); + return steal_jiffies; } #endif return false; @@ -668,26 +668,25 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static unsigned long long vtime_delta(struct task_struct *tsk) +static cputime_t vtime_delta(struct task_struct *tsk) { - unsigned long long clock; + unsigned long now = READ_ONCE(jiffies); - clock = local_clock(); - if (clock < tsk->vtime_snap) + if (time_before(now, (unsigned long)tsk->vtime_snap)) return 0; - return clock - tsk->vtime_snap; + return jiffies_to_cputime(now - tsk->vtime_snap); } static cputime_t get_vtime_delta(struct task_struct *tsk) { - unsigned long long delta = vtime_delta(tsk); + unsigned long now = READ_ONCE(jiffies); + unsigned long delta = now - tsk->vtime_snap; WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); - tsk->vtime_snap += delta; + tsk->vtime_snap = now; - /* CHECKME: always safe to convert nsecs to cputime? */ - return nsecs_to_cputime(delta); + return jiffies_to_cputime(delta); } static void __vtime_account_system(struct task_struct *tsk) @@ -699,6 +698,9 @@ static void __vtime_account_system(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { + if (!vtime_delta(tsk)) + return; + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); write_seqcount_end(&tsk->vtime_seqcount); @@ -707,7 +709,8 @@ void vtime_account_system(struct task_struct *tsk) void vtime_gen_account_irq_exit(struct task_struct *tsk) { write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; write_seqcount_end(&tsk->vtime_seqcount); @@ -718,16 +721,19 @@ void vtime_account_user(struct task_struct *tsk) cputime_t delta_cpu; write_seqcount_begin(&tsk->vtime_seqcount); - delta_cpu = get_vtime_delta(tsk); tsk->vtime_snap_whence = VTIME_SYS; - account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + if (vtime_delta(tsk)) { + delta_cpu = get_vtime_delta(tsk); + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + } write_seqcount_end(&tsk->vtime_seqcount); } void vtime_user_enter(struct task_struct *tsk) { write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); tsk->vtime_snap_whence = VTIME_USER; write_seqcount_end(&tsk->vtime_seqcount); } @@ -742,7 +748,8 @@ void vtime_guest_enter(struct task_struct *tsk) * that can thus safely catch up with a tickless delta. */ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); current->flags |= PF_VCPU; write_seqcount_end(&tsk->vtime_seqcount); } @@ -772,7 +779,7 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqcount_begin(¤t->vtime_seqcount); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock_cpu(smp_processor_id()); + current->vtime_snap = jiffies; write_seqcount_end(¤t->vtime_seqcount); } @@ -783,7 +790,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&t->vtime_seqcount); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock_cpu(cpu); + t->vtime_snap = jiffies; write_seqcount_end(&t->vtime_seqcount); local_irq_restore(flags); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 04a569c..c7a036f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -352,7 +352,15 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(!dl_se->dl_new || dl_se->dl_throttled); + WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); + + /* + * We are racing with the deadline timer. So, do nothing because + * the deadline timer handler will take care of properly recharging + * the runtime and postponing the deadline + */ + if (dl_se->dl_throttled) + return; /* * We use the regular wall clock time to set deadlines in the @@ -361,7 +369,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, */ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; - dl_se->dl_new = 0; } /* @@ -503,15 +510,6 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - /* - * The arrival of a new instance needs special treatment, i.e., - * the actual scheduling parameters have to be "renewed". - */ - if (dl_se->dl_new) { - setup_new_dl_entity(dl_se, pi_se); - return; - } - if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; @@ -608,16 +606,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) } /* - * This is possible if switched_from_dl() raced against a running - * callback that took the above !dl_task() path and we've since then - * switched back into SCHED_DEADLINE. - * - * There's nothing to do except drop our task reference. - */ - if (dl_se->dl_new) - goto unlock; - - /* * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ @@ -925,7 +913,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) + if (flags & ENQUEUE_WAKEUP) update_dl_entity(dl_se, pi_se); else if (flags & ENQUEUE_REPLENISH) replenish_dl_entity(dl_se, pi_se); @@ -1726,6 +1714,9 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { + if (dl_time_before(p->dl.deadline, rq_clock(rq))) + setup_new_dl_entity(&p->dl, &p->dl); + if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) @@ -1772,8 +1763,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, */ resched_curr(rq); #endif /* CONFIG_SMP */ - } else - switched_to_dl(rq, p); + } } const struct sched_class dl_sched_class = { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 6415117..4fbc3bd 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -16,6 +16,7 @@ #include <linux/kallsyms.h> #include <linux/utsname.h> #include <linux/mempolicy.h> +#include <linux/debugfs.h> #include "sched.h" @@ -58,6 +59,309 @@ static unsigned long nsec_low(unsigned long long nsec) #define SPLIT_NS(x) nsec_high(x), nsec_low(x) +#define SCHED_FEAT(name, enabled) \ + #name , + +static const char * const sched_feat_names[] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static int sched_feat_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (!(sysctl_sched_features & (1UL << i))) + seq_puts(m, "NO_"); + seq_printf(m, "%s ", sched_feat_names[i]); + } + seq_puts(m, "\n"); + + return 0; +} + +#ifdef HAVE_JUMP_LABEL + +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE + +#define SCHED_FEAT(name, enabled) \ + jump_label_key__##enabled , + +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static void sched_feat_disable(int i) +{ + static_key_disable(&sched_feat_keys[i]); +} + +static void sched_feat_enable(int i) +{ + static_key_enable(&sched_feat_keys[i]); +} +#else +static void sched_feat_disable(int i) { }; +static void sched_feat_enable(int i) { }; +#endif /* HAVE_JUMP_LABEL */ + +static int sched_feat_set(char *cmp) +{ + int i; + int neg = 0; + + if (strncmp(cmp, "NO_", 3) == 0) { + neg = 1; + cmp += 3; + } + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (strcmp(cmp, sched_feat_names[i]) == 0) { + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); + } + break; + } + } + + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + struct inode *inode; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + inode_lock(inode); + i = sched_feat_set(cmp); + inode_unlock(inode); + if (i == __SCHED_FEAT_NR) + return -EINVAL; + + *ppos += cnt; + + return cnt; +} + +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_feat_show, NULL); +} + +static const struct file_operations sched_feat_fops = { + .open = sched_feat_open, + .write = sched_feat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static __init int sched_init_debug(void) +{ + debugfs_create_file("sched_features", 0644, NULL, NULL, + &sched_feat_fops); + + return 0; +} +late_initcall(sched_init_debug); + +#ifdef CONFIG_SMP + +#ifdef CONFIG_SYSCTL + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + umode_t mode, proc_handler *proc_handler, + bool load_idx) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ + + return table; +} + +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_possible_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +void unregister_sched_domain_sysctl(void) +{ + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_SMP */ + #ifdef CONFIG_FAIR_GROUP_SCHED static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) { @@ -75,16 +379,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group PN(se->vruntime); PN(se->sum_exec_runtime); #ifdef CONFIG_SCHEDSTATS - PN(se->statistics.wait_start); - PN(se->statistics.sleep_start); - PN(se->statistics.block_start); - PN(se->statistics.sleep_max); - PN(se->statistics.block_max); - PN(se->statistics.exec_max); - PN(se->statistics.slice_max); - PN(se->statistics.wait_max); - PN(se->statistics.wait_sum); - P(se->statistics.wait_count); + if (schedstat_enabled()) { + PN(se->statistics.wait_start); + PN(se->statistics.sleep_start); + PN(se->statistics.block_start); + PN(se->statistics.sleep_max); + PN(se->statistics.block_max); + PN(se->statistics.exec_max); + PN(se->statistics.slice_max); + PN(se->statistics.wait_max); + PN(se->statistics.wait_sum); + P(se->statistics.wait_count); + } #endif P(se->load.weight); #ifdef CONFIG_SMP @@ -122,10 +428,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) (long long)(p->nvcsw + p->nivcsw), p->prio); #ifdef CONFIG_SCHEDSTATS - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.statistics.wait_sum), - SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.statistics.sum_sleep_runtime)); + if (schedstat_enabled()) { + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + SPLIT_NS(p->se.statistics.wait_sum), + SPLIT_NS(p->se.sum_exec_runtime), + SPLIT_NS(p->se.statistics.sum_sleep_runtime)); + } #else SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", 0LL, 0L, @@ -258,8 +566,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) { + struct dl_bw *dl_bw; + SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); +#ifdef CONFIG_SMP + dl_bw = &cpu_rq(cpu)->rd->dl_bw; +#else + dl_bw = &dl_rq->dl_bw; +#endif + SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw); + SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw); } extern __read_mostly int sched_clock_running; @@ -313,17 +630,18 @@ do { \ #define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); #define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); - P(yld_count); - - P(sched_count); - P(sched_goidle); #ifdef CONFIG_SMP P64(avg_idle); P64(max_idle_balance_cost); #endif - P(ttwu_count); - P(ttwu_local); + if (schedstat_enabled()) { + P(yld_count); + P(sched_count); + P(sched_goidle); + P(ttwu_count); + P(ttwu_local); + } #undef P #undef P64 @@ -569,38 +887,39 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) nr_switches = p->nvcsw + p->nivcsw; #ifdef CONFIG_SCHEDSTATS - PN(se.statistics.sum_sleep_runtime); - PN(se.statistics.wait_start); - PN(se.statistics.sleep_start); - PN(se.statistics.block_start); - PN(se.statistics.sleep_max); - PN(se.statistics.block_max); - PN(se.statistics.exec_max); - PN(se.statistics.slice_max); - PN(se.statistics.wait_max); - PN(se.statistics.wait_sum); - P(se.statistics.wait_count); - PN(se.statistics.iowait_sum); - P(se.statistics.iowait_count); P(se.nr_migrations); - P(se.statistics.nr_migrations_cold); - P(se.statistics.nr_failed_migrations_affine); - P(se.statistics.nr_failed_migrations_running); - P(se.statistics.nr_failed_migrations_hot); - P(se.statistics.nr_forced_migrations); - P(se.statistics.nr_wakeups); - P(se.statistics.nr_wakeups_sync); - P(se.statistics.nr_wakeups_migrate); - P(se.statistics.nr_wakeups_local); - P(se.statistics.nr_wakeups_remote); - P(se.statistics.nr_wakeups_affine); - P(se.statistics.nr_wakeups_affine_attempts); - P(se.statistics.nr_wakeups_passive); - P(se.statistics.nr_wakeups_idle); - { + if (schedstat_enabled()) { u64 avg_atom, avg_per_cpu; + PN(se.statistics.sum_sleep_runtime); + PN(se.statistics.wait_start); + PN(se.statistics.sleep_start); + PN(se.statistics.block_start); + PN(se.statistics.sleep_max); + PN(se.statistics.block_max); + PN(se.statistics.exec_max); + PN(se.statistics.slice_max); + PN(se.statistics.wait_max); + PN(se.statistics.wait_sum); + P(se.statistics.wait_count); + PN(se.statistics.iowait_sum); + P(se.statistics.iowait_count); + P(se.statistics.nr_migrations_cold); + P(se.statistics.nr_failed_migrations_affine); + P(se.statistics.nr_failed_migrations_running); + P(se.statistics.nr_failed_migrations_hot); + P(se.statistics.nr_forced_migrations); + P(se.statistics.nr_wakeups); + P(se.statistics.nr_wakeups_sync); + P(se.statistics.nr_wakeups_migrate); + P(se.statistics.nr_wakeups_local); + P(se.statistics.nr_wakeups_remote); + P(se.statistics.nr_wakeups_affine); + P(se.statistics.nr_wakeups_affine_attempts); + P(se.statistics.nr_wakeups_passive); + P(se.statistics.nr_wakeups_idle); + avg_atom = p->se.sum_exec_runtime; if (nr_switches) avg_atom = div64_ul(avg_atom, nr_switches); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cce3303..3313052 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -20,8 +20,8 @@ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ -#include <linux/latencytop.h> #include <linux/sched.h> +#include <linux/latencytop.h> #include <linux/cpumask.h> #include <linux/cpuidle.h> #include <linux/slab.h> @@ -755,7 +755,9 @@ static void update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { struct task_struct *p; - u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; + u64 delta; + + delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; if (entity_is_task(se)) { p = task_of(se); @@ -776,22 +778,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) se->statistics.wait_sum += delta; se->statistics.wait_start = 0; } -#else -static inline void -update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} - -static inline void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} -#endif /* * Task is being enqueued - update stats: */ -static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +static inline void +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { /* * Are we enqueueing a waiting task? (for current tasks @@ -802,7 +794,7 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) } static inline void -update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { /* * Mark the end of the wait period if dequeueing a @@ -810,7 +802,40 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) */ if (se != cfs_rq->curr) update_stats_wait_end(cfs_rq, se); + + if (flags & DEQUEUE_SLEEP) { + if (entity_is_task(se)) { + struct task_struct *tsk = task_of(se); + + if (tsk->state & TASK_INTERRUPTIBLE) + se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); + if (tsk->state & TASK_UNINTERRUPTIBLE) + se->statistics.block_start = rq_clock(rq_of(cfs_rq)); + } + } + +} +#else +static inline void +update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ } +#endif /* * We are picking a new current task - update its stats: @@ -907,10 +932,11 @@ struct numa_group { spinlock_t lock; /* nr_tasks, tasks */ int nr_tasks; pid_t gid; + int active_nodes; struct rcu_head rcu; - nodemask_t active_nodes; unsigned long total_faults; + unsigned long max_faults_cpu; /* * Faults_cpu is used to decide whether memory should move * towards the CPU. As a consequence, these stats are weighted @@ -969,6 +995,18 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; } +/* + * A node triggering more than 1/3 as many NUMA faults as the maximum is + * considered part of a numa group's pseudo-interleaving set. Migrations + * between these nodes are slowed down, to allow things to settle down. + */ +#define ACTIVE_NODE_FRACTION 3 + +static bool numa_is_active_node(int nid, struct numa_group *ng) +{ + return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu; +} + /* Handle placement on systems where not all nodes are directly connected. */ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, int maxdist, bool task) @@ -1118,27 +1156,23 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, return true; /* - * Do not migrate if the destination is not a node that - * is actively used by this numa group. + * Destination node is much more heavily used than the source + * node? Allow migration. */ - if (!node_isset(dst_nid, ng->active_nodes)) - return false; - - /* - * Source is a node that is not actively used by this - * numa group, while the destination is. Migrate. - */ - if (!node_isset(src_nid, ng->active_nodes)) + if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) * + ACTIVE_NODE_FRACTION) return true; /* - * Both source and destination are nodes in active - * use by this numa group. Maximize memory bandwidth - * by migrating from more heavily used groups, to less - * heavily used ones, spreading the load around. - * Use a 1/4 hysteresis to avoid spurious page movement. + * Distribute memory according to CPU & memory use on each node, + * with 3/4 hysteresis to avoid unnecessary memory migrations: + * + * faults_cpu(dst) 3 faults_cpu(src) + * --------------- * - > --------------- + * faults_mem(dst) 4 faults_mem(src) */ - return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); + return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 > + group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; } static unsigned long weighted_cpuload(const int cpu); @@ -1484,7 +1518,7 @@ static int task_numa_migrate(struct task_struct *p) .best_task = NULL, .best_imp = 0, - .best_cpu = -1 + .best_cpu = -1, }; struct sched_domain *sd; unsigned long taskweight, groupweight; @@ -1536,8 +1570,7 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && - nodes_weight(p->numa_group->active_nodes) > 1)) { + if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1572,12 +1605,14 @@ static int task_numa_migrate(struct task_struct *p) * trying for a better one later. Do not set the preferred node here. */ if (p->numa_group) { + struct numa_group *ng = p->numa_group; + if (env.best_cpu == -1) nid = env.src_nid; else nid = env.dst_nid; - if (node_isset(nid, p->numa_group->active_nodes)) + if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng)) sched_setnuma(p, env.dst_nid); } @@ -1627,20 +1662,15 @@ static void numa_migrate_preferred(struct task_struct *p) } /* - * Find the nodes on which the workload is actively running. We do this by + * Find out how many nodes on the workload is actively running on. Do this by * tracking the nodes from which NUMA hinting faults are triggered. This can * be different from the set of nodes where the workload's memory is currently * located. - * - * The bitmask is used to make smarter decisions on when to do NUMA page - * migrations, To prevent flip-flopping, and excessive page migrations, nodes - * are added when they cause over 6/16 of the maximum number of faults, but - * only removed when they drop below 3/16. */ -static void update_numa_active_node_mask(struct numa_group *numa_group) +static void numa_group_count_active_nodes(struct numa_group *numa_group) { unsigned long faults, max_faults = 0; - int nid; + int nid, active_nodes = 0; for_each_online_node(nid) { faults = group_faults_cpu(numa_group, nid); @@ -1650,12 +1680,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group) for_each_online_node(nid) { faults = group_faults_cpu(numa_group, nid); - if (!node_isset(nid, numa_group->active_nodes)) { - if (faults > max_faults * 6 / 16) - node_set(nid, numa_group->active_nodes); - } else if (faults < max_faults * 3 / 16) - node_clear(nid, numa_group->active_nodes); + if (faults * ACTIVE_NODE_FRACTION > max_faults) + active_nodes++; } + + numa_group->max_faults_cpu = max_faults; + numa_group->active_nodes = active_nodes; } /* @@ -1946,7 +1976,7 @@ static void task_numa_placement(struct task_struct *p) update_task_scan_period(p, fault_types[0], fault_types[1]); if (p->numa_group) { - update_numa_active_node_mask(p->numa_group); + numa_group_count_active_nodes(p->numa_group); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_group_nid); } @@ -1990,14 +2020,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, return; atomic_set(&grp->refcount, 1); + grp->active_nodes = 1; + grp->max_faults_cpu = 0; spin_lock_init(&grp->lock); grp->gid = p->pid; /* Second half of the array tracks nids where faults happen */ grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * nr_node_ids; - node_set(task_node(current), grp->active_nodes); - for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) grp->faults[i] = p->numa_faults[i]; @@ -2111,6 +2141,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) bool migrated = flags & TNF_MIGRATED; int cpu_node = task_node(current); int local = !!(flags & TNF_FAULT_LOCAL); + struct numa_group *ng; int priv; if (!static_branch_likely(&sched_numa_balancing)) @@ -2151,9 +2182,10 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - if (!priv && !local && p->numa_group && - node_isset(cpu_node, p->numa_group->active_nodes) && - node_isset(mem_node, p->numa_group->active_nodes)) + ng = p->numa_group; + if (!priv && !local && ng && ng->active_nodes > 1 && + numa_is_active_node(cpu_node, ng) && + numa_is_active_node(mem_node, ng)) local = 1; task_numa_placement(p); @@ -3102,6 +3134,26 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) static void check_enqueue_throttle(struct cfs_rq *cfs_rq); +static inline void check_schedstat_required(void) +{ +#ifdef CONFIG_SCHEDSTATS + if (schedstat_enabled()) + return; + + /* Force schedstat enabled if a dependent tracepoint is active */ + if (trace_sched_stat_wait_enabled() || + trace_sched_stat_sleep_enabled() || + trace_sched_stat_iowait_enabled() || + trace_sched_stat_blocked_enabled() || + trace_sched_stat_runtime_enabled()) { + pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, " + "stat_blocked and stat_runtime require the " + "kernel parameter schedstats=enabled or " + "kernel.sched_schedstats=1\n"); + } +#endif +} + static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -3122,11 +3174,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); - enqueue_sleeper(cfs_rq, se); + if (schedstat_enabled()) + enqueue_sleeper(cfs_rq, se); } - update_stats_enqueue(cfs_rq, se); - check_spread(cfs_rq, se); + check_schedstat_required(); + if (schedstat_enabled()) { + update_stats_enqueue(cfs_rq, se); + check_spread(cfs_rq, se); + } if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; @@ -3193,19 +3249,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_curr(cfs_rq); dequeue_entity_load_avg(cfs_rq, se); - update_stats_dequeue(cfs_rq, se); - if (flags & DEQUEUE_SLEEP) { -#ifdef CONFIG_SCHEDSTATS - if (entity_is_task(se)) { - struct task_struct *tsk = task_of(se); - - if (tsk->state & TASK_INTERRUPTIBLE) - se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); - if (tsk->state & TASK_UNINTERRUPTIBLE) - se->statistics.block_start = rq_clock(rq_of(cfs_rq)); - } -#endif - } + if (schedstat_enabled()) + update_stats_dequeue(cfs_rq, se, flags); clear_buddies(cfs_rq, se); @@ -3279,7 +3324,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * a CPU. So account for the time it spent waiting on the * runqueue. */ - update_stats_wait_end(cfs_rq, se); + if (schedstat_enabled()) + update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); update_load_avg(se, 1); } @@ -3292,7 +3338,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * least twice that of our own weight (i.e. dont track it * when there are only lesser-weight tasks around): */ - if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { + if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { se->statistics.slice_max = max(se->statistics.slice_max, se->sum_exec_runtime - se->prev_sum_exec_runtime); } @@ -3375,9 +3421,13 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) /* throttle cfs_rqs exceeding runtime */ check_cfs_rq_runtime(cfs_rq); - check_spread(cfs_rq, prev); + if (schedstat_enabled()) { + check_spread(cfs_rq, prev); + if (prev->on_rq) + update_stats_wait_start(cfs_rq, prev); + } + if (prev->on_rq) { - update_stats_wait_start(cfs_rq, prev); /* Put 'current' back into the tree. */ __enqueue_entity(cfs_rq, prev); /* in !on_rq case, update occurred at dequeue */ @@ -4459,9 +4509,17 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, /* scale is effectively 1 << i now, and >> i divides by scale */ - old_load = this_rq->cpu_load[i] - tickless_load; + old_load = this_rq->cpu_load[i]; old_load = decay_load_missed(old_load, pending_updates - 1, i); - old_load += tickless_load; + if (tickless_load) { + old_load -= decay_load_missed(tickless_load, pending_updates - 1, i); + /* + * old_load can never be a negative value because a + * decayed tickless_load cannot be greater than the + * original tickless_load. + */ + old_load += tickless_load; + } new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -4484,6 +4542,25 @@ static unsigned long weighted_cpuload(const int cpu) } #ifdef CONFIG_NO_HZ_COMMON +static void __update_cpu_load_nohz(struct rq *this_rq, + unsigned long curr_jiffies, + unsigned long load, + int active) +{ + unsigned long pending_updates; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + if (pending_updates) { + this_rq->last_load_update_tick = curr_jiffies; + /* + * In the regular NOHZ case, we were idle, this means load 0. + * In the NOHZ_FULL case, we were non-idle, we should consider + * its weighted load. + */ + __update_cpu_load(this_rq, load, pending_updates, active); + } +} + /* * There is no sane way to deal with nohz on smp when using jiffies because the * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading @@ -4501,22 +4578,15 @@ static unsigned long weighted_cpuload(const int cpu) * Called from nohz_idle_balance() to update the load ratings before doing the * idle balance. */ -static void update_idle_cpu_load(struct rq *this_rq) +static void update_cpu_load_idle(struct rq *this_rq) { - unsigned long curr_jiffies = READ_ONCE(jiffies); - unsigned long load = weighted_cpuload(cpu_of(this_rq)); - unsigned long pending_updates; - /* * bail if there's load or we're actually up-to-date. */ - if (load || curr_jiffies == this_rq->last_load_update_tick) + if (weighted_cpuload(cpu_of(this_rq))) return; - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - this_rq->last_load_update_tick = curr_jiffies; - - __update_cpu_load(this_rq, load, pending_updates, 0); + __update_cpu_load_nohz(this_rq, READ_ONCE(jiffies), 0, 0); } /* @@ -4527,22 +4597,12 @@ void update_cpu_load_nohz(int active) struct rq *this_rq = this_rq(); unsigned long curr_jiffies = READ_ONCE(jiffies); unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0; - unsigned long pending_updates; if (curr_jiffies == this_rq->last_load_update_tick) return; raw_spin_lock(&this_rq->lock); - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - if (pending_updates) { - this_rq->last_load_update_tick = curr_jiffies; - /* - * In the regular NOHZ case, we were idle, this means load 0. - * In the NOHZ_FULL case, we were non-idle, we should consider - * its weighted load. - */ - __update_cpu_load(this_rq, load, pending_updates, active); - } + __update_cpu_load_nohz(this_rq, curr_jiffies, load, active); raw_spin_unlock(&this_rq->lock); } #endif /* CONFIG_NO_HZ */ @@ -4554,7 +4614,7 @@ void update_cpu_load_active(struct rq *this_rq) { unsigned long load = weighted_cpuload(cpu_of(this_rq)); /* - * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). + * See the mess around update_cpu_load_idle() / update_cpu_load_nohz(). */ this_rq->last_load_update_tick = jiffies; __update_cpu_load(this_rq, load, 1, 1); @@ -7848,7 +7908,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) if (time_after_eq(jiffies, rq->next_balance)) { raw_spin_lock_irq(&rq->lock); update_rq_clock(rq); - update_idle_cpu_load(rq); + update_cpu_load_idle(rq); raw_spin_unlock_irq(&rq->lock); rebalance_domains(rq, CPU_IDLE); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 544a713..bd12c6c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/cpu.h> #include <linux/cpuidle.h> +#include <linux/cpuhotplug.h> #include <linux/tick.h> #include <linux/mm.h> #include <linux/stackprotector.h> @@ -193,8 +194,6 @@ exit_idle: rcu_idle_exit(); } -DEFINE_PER_CPU(bool, cpu_dead_idle); - /* * Generic idle loop implementation * @@ -221,10 +220,7 @@ static void cpu_idle_loop(void) rmb(); if (cpu_is_offline(smp_processor_id())) { - rcu_cpu_notify(NULL, CPU_DYING_IDLE, - (void *)(long)smp_processor_id()); - smp_mb(); /* all activity before dead. */ - this_cpu_write(cpu_dead_idle, true); + cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } @@ -291,5 +287,6 @@ void cpu_startup_entry(enum cpuhp_state state) boot_init_stack_canary(); #endif arch_cpu_idle_prepare(); + cpuhp_online_idle(state); cpu_idle_loop(); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86ab..5624713 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -58,7 +58,15 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_lock(&rt_b->rt_runtime_lock); if (!rt_b->rt_period_active) { rt_b->rt_period_active = 1; - hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period); + /* + * SCHED_DEADLINE updates the bandwidth, as a run away + * RT task with a DL task could hog a CPU. But DL does + * not reset the period. If a deadline task was running + * without an RT task running, it can cause RT tasks to + * throttle when they start up. Kick the timer right away + * to update the period. + */ + hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0)); hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); } raw_spin_unlock(&rt_b->rt_runtime_lock); @@ -436,7 +444,7 @@ static void dequeue_top_rt_rq(struct rt_rq *rt_rq); static inline int on_rt_rq(struct sched_rt_entity *rt_se) { - return !list_empty(&rt_se->run_list); + return rt_se->on_rq; } #ifdef CONFIG_RT_GROUP_SCHED @@ -482,8 +490,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) return rt_se->my_q; } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head); -static void dequeue_rt_entity(struct sched_rt_entity *rt_se); +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { @@ -499,7 +507,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) if (!rt_se) enqueue_top_rt_rq(rt_rq); else if (!on_rt_rq(rt_se)) - enqueue_rt_entity(rt_se, false); + enqueue_rt_entity(rt_se, 0); if (rt_rq->highest_prio.curr < curr->prio) resched_curr(rq); @@ -516,7 +524,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) if (!rt_se) dequeue_top_rt_rq(rt_rq); else if (on_rt_rq(rt_se)) - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, 0); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -1142,12 +1150,27 @@ unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) } static inline +unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + struct task_struct *tsk; + + if (group_rq) + return group_rq->rr_nr_running; + + tsk = rt_task_of(rt_se); + + return (tsk->policy == SCHED_RR) ? 1 : 0; +} + +static inline void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { int prio = rt_se_prio(rt_se); WARN_ON(!rt_prio(prio)); rt_rq->rt_nr_running += rt_se_nr_running(rt_se); + rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se); inc_rt_prio(rt_rq, prio); inc_rt_migration(rt_se, rt_rq); @@ -1160,13 +1183,37 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); + rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se); dec_rt_prio(rt_rq, rt_se_prio(rt_se)); dec_rt_migration(rt_se, rt_rq); dec_rt_group(rt_se, rt_rq); } -static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +/* + * Change rt_se->run_list location unless SAVE && !MOVE + * + * assumes ENQUEUE/DEQUEUE flags match + */ +static inline bool move_entity(unsigned int flags) +{ + if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE) + return false; + + return true; +} + +static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array) +{ + list_del_init(&rt_se->run_list); + + if (list_empty(array->queue + rt_se_prio(rt_se))) + __clear_bit(rt_se_prio(rt_se), array->bitmap); + + rt_se->on_list = 0; +} + +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; @@ -1179,26 +1226,37 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) * get throttled and the current group doesn't have any other * active members. */ - if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) { + if (rt_se->on_list) + __delist_rt_entity(rt_se, array); return; + } - if (head) - list_add(&rt_se->run_list, queue); - else - list_add_tail(&rt_se->run_list, queue); - __set_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(rt_se->on_list); + if (flags & ENQUEUE_HEAD) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + + __set_bit(rt_se_prio(rt_se), array->bitmap); + rt_se->on_list = 1; + } + rt_se->on_rq = 1; inc_rt_tasks(rt_se, rt_rq); } -static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; - list_del_init(&rt_se->run_list); - if (list_empty(array->queue + rt_se_prio(rt_se))) - __clear_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(!rt_se->on_list); + __delist_rt_entity(rt_se, array); + } + rt_se->on_rq = 0; dec_rt_tasks(rt_se, rt_rq); } @@ -1207,7 +1265,7 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) * Because the prio of an upper entry depends on the lower * entries, we must remove entries top - down. */ -static void dequeue_rt_stack(struct sched_rt_entity *rt_se) +static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags) { struct sched_rt_entity *back = NULL; @@ -1220,31 +1278,31 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) - __dequeue_rt_entity(rt_se); + __dequeue_rt_entity(rt_se, flags); } } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) - __enqueue_rt_entity(rt_se, head); + __enqueue_rt_entity(rt_se, flags); enqueue_top_rt_rq(&rq->rt); } -static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); if (rt_rq && rt_rq->rt_nr_running) - __enqueue_rt_entity(rt_se, false); + __enqueue_rt_entity(rt_se, flags); } enqueue_top_rt_rq(&rq->rt); } @@ -1260,7 +1318,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (flags & ENQUEUE_WAKEUP) rt_se->timeout = 0; - enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + enqueue_rt_entity(rt_se, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); @@ -1271,7 +1329,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, flags); dequeue_pushable_task(rq, p); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4f6598a..e6d4a3f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3,6 +3,7 @@ #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> +#include <linux/binfmts.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> @@ -318,7 +319,6 @@ extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, struct sched_entity *se, int cpu, struct sched_entity *parent); extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); -extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); @@ -450,6 +450,7 @@ static inline int rt_bandwidth_enabled(void) struct rt_rq { struct rt_prio_array active; unsigned int rt_nr_running; + unsigned int rr_nr_running; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED struct { int curr; /* highest queued rt task prio */ @@ -909,6 +910,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group) extern int group_balance_cpu(struct sched_group *sg); +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) +void register_sched_domain_sysctl(void); +void unregister_sched_domain_sysctl(void); +#else +static inline void register_sched_domain_sysctl(void) +{ +} +static inline void unregister_sched_domain_sysctl(void) +{ +} +#endif + #else static inline void sched_ttwu_pending(void) { } @@ -1022,6 +1035,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ extern struct static_key_false sched_numa_balancing; +extern struct static_key_false sched_schedstats; static inline u64 global_rt_period(void) { @@ -1130,18 +1144,40 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) extern const int sched_prio_to_weight[40]; extern const u32 sched_prio_to_wmult[40]; +/* + * {de,en}queue flags: + * + * DEQUEUE_SLEEP - task is no longer runnable + * ENQUEUE_WAKEUP - task just became runnable + * + * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks + * are in a known state which allows modification. Such pairs + * should preserve as much state as possible. + * + * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location + * in the runqueue. + * + * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) + * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) + * ENQUEUE_WAKING - sched_class::task_waking was called + * + */ + +#define DEQUEUE_SLEEP 0x01 +#define DEQUEUE_SAVE 0x02 /* matches ENQUEUE_RESTORE */ +#define DEQUEUE_MOVE 0x04 /* matches ENQUEUE_MOVE */ + #define ENQUEUE_WAKEUP 0x01 -#define ENQUEUE_HEAD 0x02 +#define ENQUEUE_RESTORE 0x02 +#define ENQUEUE_MOVE 0x04 + +#define ENQUEUE_HEAD 0x08 +#define ENQUEUE_REPLENISH 0x10 #ifdef CONFIG_SMP -#define ENQUEUE_WAKING 0x04 /* sched_class::task_waking was called */ +#define ENQUEUE_WAKING 0x20 #else #define ENQUEUE_WAKING 0x00 #endif -#define ENQUEUE_REPLENISH 0x08 -#define ENQUEUE_RESTORE 0x10 - -#define DEQUEUE_SLEEP 0x01 -#define DEQUEUE_SAVE 0x02 #define RETRY_TASK ((void *)-1UL) @@ -1278,6 +1314,35 @@ unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); +#ifdef CONFIG_NO_HZ_FULL +extern bool sched_can_stop_tick(struct rq *rq); + +/* + * Tick may be needed by tasks in the runqueue depending on their policy and + * requirements. If tick is needed, lets send the target an IPI to kick it out of + * nohz mode if necessary. + */ +static inline void sched_update_tick_dependency(struct rq *rq) +{ + int cpu; + + if (!tick_nohz_full_enabled()) + return; + + cpu = cpu_of(rq); + + if (!tick_nohz_full_cpu(cpu)) + return; + + if (sched_can_stop_tick(rq)) + tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED); + else + tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); +} +#else +static inline void sched_update_tick_dependency(struct rq *rq) { } +#endif + static inline void add_nr_running(struct rq *rq, unsigned count) { unsigned prev_nr = rq->nr_running; @@ -1289,26 +1354,16 @@ static inline void add_nr_running(struct rq *rq, unsigned count) if (!rq->rd->overload) rq->rd->overload = true; #endif - -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_cpu(rq->cpu)) { - /* - * Tick is needed if more than one task runs on a CPU. - * Send the target an IPI to kick it out of nohz mode. - * - * We assume that IPI implies full memory barrier and the - * new value of rq->nr_running is visible on reception - * from the target. - */ - tick_nohz_full_kick_cpu(rq->cpu); - } -#endif } + + sched_update_tick_dependency(rq); } static inline void sub_nr_running(struct rq *rq, unsigned count) { rq->nr_running -= count; + /* Check if we still need preemption */ + sched_update_tick_dependency(rq); } static inline void rq_last_tick_reset(struct rq *rq) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index b0fbc76..70b3b6a 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) if (rq) rq->rq_sched_info.run_delay += delta; } -# define schedstat_inc(rq, field) do { (rq)->field++; } while (0) -# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) -# define schedstat_set(var, val) do { var = (val); } while (0) +# define schedstat_enabled() static_branch_unlikely(&sched_schedstats) +# define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0) +# define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0) +# define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) #else /* !CONFIG_SCHEDSTATS */ static inline void rq_sched_info_arrive(struct rq *rq, unsigned long long delta) @@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) {} +# define schedstat_enabled() 0 # define schedstat_inc(rq, field) do { } while (0) # define schedstat_add(rq, field, amt) do { } while (0) # define schedstat_set(var, val) do { } while (0) diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c new file mode 100644 index 0000000..82f0dff --- /dev/null +++ b/kernel/sched/swait.c @@ -0,0 +1,123 @@ +#include <linux/sched.h> +#include <linux/swait.h> + +void __init_swait_queue_head(struct swait_queue_head *q, const char *name, + struct lock_class_key *key) +{ + raw_spin_lock_init(&q->lock); + lockdep_set_class_and_name(&q->lock, key, name); + INIT_LIST_HEAD(&q->task_list); +} +EXPORT_SYMBOL(__init_swait_queue_head); + +/* + * The thing about the wake_up_state() return value; I think we can ignore it. + * + * If for some reason it would return 0, that means the previously waiting + * task is already running, so it will observe condition true (or has already). + */ +void swake_up_locked(struct swait_queue_head *q) +{ + struct swait_queue *curr; + + if (list_empty(&q->task_list)) + return; + + curr = list_first_entry(&q->task_list, typeof(*curr), task_list); + wake_up_process(curr->task); + list_del_init(&curr->task_list); +} +EXPORT_SYMBOL(swake_up_locked); + +void swake_up(struct swait_queue_head *q) +{ + unsigned long flags; + + if (!swait_active(q)) + return; + + raw_spin_lock_irqsave(&q->lock, flags); + swake_up_locked(q); + raw_spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(swake_up); + +/* + * Does not allow usage from IRQ disabled, since we must be able to + * release IRQs to guarantee bounded hold time. + */ +void swake_up_all(struct swait_queue_head *q) +{ + struct swait_queue *curr; + LIST_HEAD(tmp); + + if (!swait_active(q)) + return; + + raw_spin_lock_irq(&q->lock); + list_splice_init(&q->task_list, &tmp); + while (!list_empty(&tmp)) { + curr = list_first_entry(&tmp, typeof(*curr), task_list); + + wake_up_state(curr->task, TASK_NORMAL); + list_del_init(&curr->task_list); + + if (list_empty(&tmp)) + break; + + raw_spin_unlock_irq(&q->lock); + raw_spin_lock_irq(&q->lock); + } + raw_spin_unlock_irq(&q->lock); +} +EXPORT_SYMBOL(swake_up_all); + +void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + wait->task = current; + if (list_empty(&wait->task_list)) + list_add(&wait->task_list, &q->task_list); +} + +void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&q->lock, flags); + __prepare_to_swait(q, wait); + set_current_state(state); + raw_spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_swait); + +long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) +{ + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + prepare_to_swait(q, wait, state); + + return 0; +} +EXPORT_SYMBOL(prepare_to_swait_event); + +void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + __set_current_state(TASK_RUNNING); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); +} + +void finish_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + + if (!list_empty_careful(&wait->task_list)) { + raw_spin_lock_irqsave(&q->lock, flags); + list_del_init(&wait->task_list); + raw_spin_unlock_irqrestore(&q->lock, flags); + } +} +EXPORT_SYMBOL(finish_swait); diff --git a/kernel/smp.c b/kernel/smp.c index d903c02..7416544 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -105,13 +105,12 @@ void __init call_function_init(void) * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void csd_lock_wait(struct call_single_data *csd) +static __always_inline void csd_lock_wait(struct call_single_data *csd) { - while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK) - cpu_relax(); + smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK)); } -static void csd_lock(struct call_single_data *csd) +static __always_inline void csd_lock(struct call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; @@ -124,7 +123,7 @@ static void csd_lock(struct call_single_data *csd) smp_wmb(); } -static void csd_unlock(struct call_single_data *csd) +static __always_inline void csd_unlock(struct call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); @@ -569,6 +568,7 @@ void __init smp_init(void) unsigned int cpu; idle_threads_init(); + cpuhp_threads_init(); /* FIXME: This should be done in userspace --RR */ for_each_present_cpu(cpu) { diff --git a/kernel/smpboot.c b/kernel/smpboot.c index d264f59..13bc43d 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -226,7 +226,7 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp kthread_unpark(tsk); } -void smpboot_unpark_threads(unsigned int cpu) +int smpboot_unpark_threads(unsigned int cpu) { struct smp_hotplug_thread *cur; @@ -235,6 +235,7 @@ void smpboot_unpark_threads(unsigned int cpu) if (cpumask_test_cpu(cpu, cur->cpumask)) smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); + return 0; } static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) @@ -245,7 +246,7 @@ static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kthread_park(tsk); } -void smpboot_park_threads(unsigned int cpu) +int smpboot_park_threads(unsigned int cpu) { struct smp_hotplug_thread *cur; @@ -253,6 +254,7 @@ void smpboot_park_threads(unsigned int cpu) list_for_each_entry_reverse(cur, &hotplug_threads, list) smpboot_park_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); + return 0; } static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 72415a0..485b81c 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -14,7 +14,9 @@ static inline void idle_threads_init(void) { } #endif int smpboot_create_threads(unsigned int cpu); -void smpboot_park_threads(unsigned int cpu); -void smpboot_unpark_threads(unsigned int cpu); +int smpboot_park_threads(unsigned int cpu); +int smpboot_unpark_threads(unsigned int cpu); + +void __init cpuhp_threads_init(void); #endif diff --git a/kernel/softirq.c b/kernel/softirq.c index 479e443..8aae49d 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -116,9 +116,9 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) if (preempt_count() == cnt) { #ifdef CONFIG_DEBUG_PREEMPT - current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); + current->preempt_disable_ip = get_lock_parent_ip(); #endif - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); } } EXPORT_SYMBOL(__local_bh_disable_ip); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 97715fd..f5102fab 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -350,6 +350,17 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_SCHEDSTATS + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SCHEDSTATS */ #endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING { @@ -505,7 +516,7 @@ static struct ctl_table kern_table[] = { .data = &latencytop_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = sysctl_latencytop, }, #endif #ifdef CONFIG_BLK_DEV_INITRD diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 664de53..56ece14 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) /* cs is a watchdog. */ if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_select_watchdog(bool fallback) +{ + struct clocksource *cs, *old_wd; + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + /* save current watchdog */ + old_wd = watchdog; + if (fallback) + watchdog = NULL; + + list_for_each_entry(cs, &clocksource_list, list) { + /* cs is a clocksource to be watched. */ + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) + continue; + + /* Skip current if we were requested for a fallback. */ + if (fallback && cs == old_wd) + continue; + /* Pick the best watchdog. */ - if (!watchdog || cs->rating > watchdog->rating) { + if (!watchdog || cs->rating > watchdog->rating) watchdog = cs; - /* Reset watchdog cycles */ - clocksource_reset_watchdog(); - } } + /* If we failed to find a fallback restore the old one. */ + if (!watchdog) + watchdog = old_wd; + + /* If we changed the watchdog we need to reset cycles. */ + if (watchdog != old_wd) + clocksource_reset_watchdog(); + /* Check if the watchdog timer needs to be started. */ clocksource_start_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); @@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; } +static void clocksource_select_watchdog(bool fallback) { } static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } static inline int __clocksource_watchdog_kthread(void) { return 0; } @@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_enqueue(cs); clocksource_enqueue_watchdog(cs); clocksource_select(); + clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); return 0; } @@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating) mutex_lock(&clocksource_mutex); __clocksource_change_rating(cs, rating); clocksource_select(); + clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); @@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating); */ static int clocksource_unbind(struct clocksource *cs) { - /* - * I really can't convince myself to support this on hardware - * designed by lobotomized monkeys. - */ - if (clocksource_is_watchdog(cs)) - return -EBUSY; + if (clocksource_is_watchdog(cs)) { + /* Select and try to install a replacement watchdog. */ + clocksource_select_watchdog(true); + if (clocksource_is_watchdog(cs)) + return -EBUSY; + } if (cs == curr_clocksource) { /* Select and try to install a replacement clock source */ diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 347fecf..555e21f 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -68,7 +68,7 @@ static struct clocksource clocksource_jiffies = { .name = "jiffies", .rating = 1, /* lowest valid rating*/ .read = jiffies_read, - .mask = 0xffffffff, /*32bits*/ + .mask = CLOCKSOURCE_MASK(32), .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ .shift = JIFFIES_SHIFT, .max_cycles = 10, diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index f5e86d2..1cafba8 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -333,7 +333,6 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) return err; } - /* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. * This is called from sys_timer_create() and do_cpu_nanosleep() with the @@ -517,6 +516,10 @@ static void arm_timer(struct k_itimer *timer) cputime_expires->sched_exp = exp; break; } + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); + else + tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER); } } @@ -582,39 +585,6 @@ static int cpu_timer_sample_group(const clockid_t which_clock, return 0; } -#ifdef CONFIG_NO_HZ_FULL -static void nohz_kick_work_fn(struct work_struct *work) -{ - tick_nohz_full_kick_all(); -} - -static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn); - -/* - * We need the IPIs to be sent from sane process context. - * The posix cpu timers are always set with irqs disabled. - */ -static void posix_cpu_timer_kick_nohz(void) -{ - if (context_tracking_is_enabled()) - schedule_work(&nohz_kick_work); -} - -bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk) -{ - if (!task_cputime_zero(&tsk->cputime_expires)) - return false; - - /* Check if cputimer is running. This is accessed without locking. */ - if (READ_ONCE(tsk->signal->cputimer.running)) - return false; - - return true; -} -#else -static inline void posix_cpu_timer_kick_nohz(void) { } -#endif - /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. @@ -761,8 +731,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, sample_to_timespec(timer->it_clock, old_incr, &old->it_interval); } - if (!ret) - posix_cpu_timer_kick_nohz(); + return ret; } @@ -911,6 +880,8 @@ static void check_thread_timers(struct task_struct *tsk, __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); } } + if (task_cputime_zero(tsk_expires)) + tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER); } static inline void stop_process_timers(struct signal_struct *sig) @@ -919,6 +890,7 @@ static inline void stop_process_timers(struct signal_struct *sig) /* Turn off cputimer->running. This is done without locking. */ WRITE_ONCE(cputimer->running, false); + tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } static u32 onecputick; @@ -1095,8 +1067,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) arm_timer(timer); unlock_task_sighand(p, &flags); - /* Kick full dynticks CPUs in case they need to tick on the new timer */ - posix_cpu_timer_kick_nohz(); out: timer->it_overrun_last = timer->it_overrun; timer->it_overrun = -1; @@ -1270,7 +1240,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } if (!*newval) - goto out; + return; *newval += now; } @@ -1288,8 +1258,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, tsk->signal->cputime_expires.virt_exp = *newval; break; } -out: - posix_cpu_timer_kick_nohz(); + + tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER); } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0b17424..969e670 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -22,7 +22,6 @@ #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> -#include <linux/perf_event.h> #include <linux/context_tracking.h> #include <asm/irq_regs.h> @@ -158,54 +157,63 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) cpumask_var_t tick_nohz_full_mask; cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; +static unsigned long tick_dep_mask; -static bool can_stop_full_tick(void) +static void trace_tick_dependency(unsigned long dep) +{ + if (dep & TICK_DEP_MASK_POSIX_TIMER) { + trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); + return; + } + + if (dep & TICK_DEP_MASK_PERF_EVENTS) { + trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); + return; + } + + if (dep & TICK_DEP_MASK_SCHED) { + trace_tick_stop(0, TICK_DEP_MASK_SCHED); + return; + } + + if (dep & TICK_DEP_MASK_CLOCK_UNSTABLE) + trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); +} + +static bool can_stop_full_tick(struct tick_sched *ts) { WARN_ON_ONCE(!irqs_disabled()); - if (!sched_can_stop_tick()) { - trace_tick_stop(0, "more than 1 task in runqueue\n"); + if (tick_dep_mask) { + trace_tick_dependency(tick_dep_mask); return false; } - if (!posix_cpu_timers_can_stop_tick(current)) { - trace_tick_stop(0, "posix timers running\n"); + if (ts->tick_dep_mask) { + trace_tick_dependency(ts->tick_dep_mask); return false; } - if (!perf_event_can_stop_tick()) { - trace_tick_stop(0, "perf events running\n"); + if (current->tick_dep_mask) { + trace_tick_dependency(current->tick_dep_mask); return false; } - /* sched_clock_tick() needs us? */ -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK - /* - * TODO: kick full dynticks CPUs when - * sched_clock_stable is set. - */ - if (!sched_clock_stable()) { - trace_tick_stop(0, "unstable sched clock\n"); - /* - * Don't allow the user to think they can get - * full NO_HZ with this machine. - */ - WARN_ONCE(tick_nohz_full_running, - "NO_HZ FULL will not work with unstable sched clock"); + if (current->signal->tick_dep_mask) { + trace_tick_dependency(current->signal->tick_dep_mask); return false; } -#endif return true; } -static void nohz_full_kick_work_func(struct irq_work *work) +static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { - .func = nohz_full_kick_work_func, + .func = nohz_full_kick_func, }; /* @@ -214,7 +222,7 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ -void tick_nohz_full_kick(void) +static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; @@ -234,27 +242,112 @@ void tick_nohz_full_kick_cpu(int cpu) irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } -static void nohz_full_kick_ipi(void *info) -{ - /* Empty, the tick restart happens on tick_nohz_irq_exit() */ -} - /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ -void tick_nohz_full_kick_all(void) +static void tick_nohz_full_kick_all(void) { + int cpu; + if (!tick_nohz_full_running) return; preempt_disable(); - smp_call_function_many(tick_nohz_full_mask, - nohz_full_kick_ipi, NULL, false); - tick_nohz_full_kick(); + for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) + tick_nohz_full_kick_cpu(cpu); preempt_enable(); } +static void tick_nohz_dep_set_all(unsigned long *dep, + enum tick_dep_bits bit) +{ + unsigned long prev; + + prev = fetch_or(dep, BIT_MASK(bit)); + if (!prev) + tick_nohz_full_kick_all(); +} + +/* + * Set a global tick dependency. Used by perf events that rely on freq and + * by unstable clock. + */ +void tick_nohz_dep_set(enum tick_dep_bits bit) +{ + tick_nohz_dep_set_all(&tick_dep_mask, bit); +} + +void tick_nohz_dep_clear(enum tick_dep_bits bit) +{ + clear_bit(bit, &tick_dep_mask); +} + +/* + * Set per-CPU tick dependency. Used by scheduler and perf events in order to + * manage events throttling. + */ +void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) +{ + unsigned long prev; + struct tick_sched *ts; + + ts = per_cpu_ptr(&tick_cpu_sched, cpu); + + prev = fetch_or(&ts->tick_dep_mask, BIT_MASK(bit)); + if (!prev) { + preempt_disable(); + /* Perf needs local kick that is NMI safe */ + if (cpu == smp_processor_id()) { + tick_nohz_full_kick(); + } else { + /* Remote irq work not NMI-safe */ + if (!WARN_ON_ONCE(in_nmi())) + tick_nohz_full_kick_cpu(cpu); + } + preempt_enable(); + } +} + +void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) +{ + struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); + + clear_bit(bit, &ts->tick_dep_mask); +} + +/* + * Set a per-task tick dependency. Posix CPU timers need this in order to elapse + * per task timers. + */ +void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) +{ + /* + * We could optimize this with just kicking the target running the task + * if that noise matters for nohz full users. + */ + tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit); +} + +void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) +{ + clear_bit(bit, &tsk->tick_dep_mask); +} + +/* + * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse + * per process timers. + */ +void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit) +{ + tick_nohz_dep_set_all(&sig->tick_dep_mask, bit); +} + +void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) +{ + clear_bit(bit, &sig->tick_dep_mask); +} + /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: @@ -263,15 +356,19 @@ void tick_nohz_full_kick_all(void) void __tick_nohz_task_switch(void) { unsigned long flags; + struct tick_sched *ts; local_irq_save(flags); if (!tick_nohz_full_cpu(smp_processor_id())) goto out; - if (tick_nohz_tick_stopped() && !can_stop_full_tick()) - tick_nohz_full_kick(); + ts = this_cpu_ptr(&tick_cpu_sched); + if (ts->tick_stopped) { + if (current->tick_dep_mask || current->signal->tick_dep_mask) + tick_nohz_full_kick(); + } out: local_irq_restore(flags); } @@ -689,7 +786,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; - trace_tick_stop(1, " "); + trace_tick_stop(1, TICK_DEP_MASK_NONE); } /* @@ -740,7 +837,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) return; - if (can_stop_full_tick()) + if (can_stop_full_tick(ts)) tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, ktime_get(), 1); diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index a4a8d4e..eb4e325 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -60,6 +60,7 @@ struct tick_sched { u64 next_timer; ktime_t idle_expires; int do_timer_last; + unsigned long tick_dep_mask; }; extern struct tick_sched *tick_get_tick_sched(int cpu); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 34b4ced..9c629bb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -233,6 +233,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; + ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.read = clock->read; @@ -298,17 +299,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; static inline u32 arch_gettimeoffset(void) { return 0; } #endif +static inline s64 timekeeping_delta_to_ns(struct tk_read_base *tkr, + cycle_t delta) +{ + s64 nsec; + + nsec = delta * tkr->mult + tkr->xtime_nsec; + nsec >>= tkr->shift; + + /* If arch requires, add in get_arch_timeoffset() */ + return nsec + arch_gettimeoffset(); +} + static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) { cycle_t delta; - s64 nsec; delta = timekeeping_get_delta(tkr); + return timekeeping_delta_to_ns(tkr, delta); +} - nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift; +static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, + cycle_t cycles) +{ + cycle_t delta; - /* If arch requires, add in get_arch_timeoffset() */ - return nsec + arch_gettimeoffset(); + /* calculate the delta since the last update_wall_time */ + delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); + return timekeeping_delta_to_ns(tkr, delta); } /** @@ -857,44 +875,262 @@ time64_t __ktime_get_real_seconds(void) return tk->xtime_sec; } +/** + * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter + * @systime_snapshot: pointer to struct receiving the system time snapshot + */ +void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long seq; + ktime_t base_raw; + ktime_t base_real; + s64 nsec_raw; + s64 nsec_real; + cycle_t now; -#ifdef CONFIG_NTP_PPS + WARN_ON_ONCE(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + + now = tk->tkr_mono.read(tk->tkr_mono.clock); + systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; + systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; + base_real = ktime_add(tk->tkr_mono.base, + tk_core.timekeeper.offs_real); + base_raw = tk->tkr_raw.base; + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + systime_snapshot->cycles = now; + systime_snapshot->real = ktime_add_ns(base_real, nsec_real); + systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); +} +EXPORT_SYMBOL_GPL(ktime_get_snapshot); + +/* Scale base by mult/div checking for overflow */ +static int scale64_check_overflow(u64 mult, u64 div, u64 *base) +{ + u64 tmp, rem; + + tmp = div64_u64_rem(*base, div, &rem); + + if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || + ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) + return -EOVERFLOW; + tmp *= mult; + rem *= mult; + + do_div(rem, div); + *base = tmp + rem; + return 0; +} /** - * ktime_get_raw_and_real_ts64 - get day and raw monotonic time in timespec format - * @ts_raw: pointer to the timespec to be set to raw monotonic time - * @ts_real: pointer to the timespec to be set to the time of day + * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval + * @history: Snapshot representing start of history + * @partial_history_cycles: Cycle offset into history (fractional part) + * @total_history_cycles: Total history length in cycles + * @discontinuity: True indicates clock was set on history period + * @ts: Cross timestamp that should be adjusted using + * partial/total ratio * - * This function reads both the time of day and raw monotonic time at the - * same time atomically and stores the resulting timestamps in timespec - * format. + * Helper function used by get_device_system_crosststamp() to correct the + * crosstimestamp corresponding to the start of the current interval to the + * system counter value (timestamp point) provided by the driver. The + * total_history_* quantities are the total history starting at the provided + * reference point and ending at the start of the current interval. The cycle + * count between the driver timestamp point and the start of the current + * interval is partial_history_cycles. */ -void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real) +static int adjust_historical_crosststamp(struct system_time_snapshot *history, + cycle_t partial_history_cycles, + cycle_t total_history_cycles, + bool discontinuity, + struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; - s64 nsecs_raw, nsecs_real; + u64 corr_raw, corr_real; + bool interp_forward; + int ret; - WARN_ON_ONCE(timekeeping_suspended); + if (total_history_cycles == 0 || partial_history_cycles == 0) + return 0; + + /* Interpolate shortest distance from beginning or end of history */ + interp_forward = partial_history_cycles > total_history_cycles/2 ? + true : false; + partial_history_cycles = interp_forward ? + total_history_cycles - partial_history_cycles : + partial_history_cycles; + + /* + * Scale the monotonic raw time delta by: + * partial_history_cycles / total_history_cycles + */ + corr_raw = (u64)ktime_to_ns( + ktime_sub(ts->sys_monoraw, history->raw)); + ret = scale64_check_overflow(partial_history_cycles, + total_history_cycles, &corr_raw); + if (ret) + return ret; + + /* + * If there is a discontinuity in the history, scale monotonic raw + * correction by: + * mult(real)/mult(raw) yielding the realtime correction + * Otherwise, calculate the realtime correction similar to monotonic + * raw calculation + */ + if (discontinuity) { + corr_real = mul_u64_u32_div + (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); + } else { + corr_real = (u64)ktime_to_ns( + ktime_sub(ts->sys_realtime, history->real)); + ret = scale64_check_overflow(partial_history_cycles, + total_history_cycles, &corr_real); + if (ret) + return ret; + } + + /* Fixup monotonic raw and real time time values */ + if (interp_forward) { + ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); + ts->sys_realtime = ktime_add_ns(history->real, corr_real); + } else { + ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); + ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); + } + + return 0; +} + +/* + * cycle_between - true if test occurs chronologically between before and after + */ +static bool cycle_between(cycle_t before, cycle_t test, cycle_t after) +{ + if (test > before && test < after) + return true; + if (test < before && before > after) + return true; + return false; +} + +/** + * get_device_system_crosststamp - Synchronously capture system/device timestamp + * @get_time_fn: Callback to get simultaneous device time and + * system counter from the device driver + * @ctx: Context passed to get_time_fn() + * @history_begin: Historical reference point used to interpolate system + * time when counter provided by the driver is before the current interval + * @xtstamp: Receives simultaneously captured system and device time + * + * Reads a timestamp from a device and correlates it to system time + */ +int get_device_system_crosststamp(int (*get_time_fn) + (ktime_t *device_time, + struct system_counterval_t *sys_counterval, + void *ctx), + void *ctx, + struct system_time_snapshot *history_begin, + struct system_device_crosststamp *xtstamp) +{ + struct system_counterval_t system_counterval; + struct timekeeper *tk = &tk_core.timekeeper; + cycle_t cycles, now, interval_start; + unsigned int clock_was_set_seq = 0; + ktime_t base_real, base_raw; + s64 nsec_real, nsec_raw; + u8 cs_was_changed_seq; + unsigned long seq; + bool do_interp; + int ret; do { seq = read_seqcount_begin(&tk_core.seq); + /* + * Try to synchronously capture device time and a system + * counter value calling back into the device driver + */ + ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); + if (ret) + return ret; + + /* + * Verify that the clocksource associated with the captured + * system counter value is the same as the currently installed + * timekeeper clocksource + */ + if (tk->tkr_mono.clock != system_counterval.cs) + return -ENODEV; + cycles = system_counterval.cycles; - *ts_raw = tk->raw_time; - ts_real->tv_sec = tk->xtime_sec; - ts_real->tv_nsec = 0; + /* + * Check whether the system counter value provided by the + * device driver is on the current timekeeping interval. + */ + now = tk->tkr_mono.read(tk->tkr_mono.clock); + interval_start = tk->tkr_mono.cycle_last; + if (!cycle_between(interval_start, cycles, now)) { + clock_was_set_seq = tk->clock_was_set_seq; + cs_was_changed_seq = tk->cs_was_changed_seq; + cycles = interval_start; + do_interp = true; + } else { + do_interp = false; + } - nsecs_raw = timekeeping_get_ns(&tk->tkr_raw); - nsecs_real = timekeeping_get_ns(&tk->tkr_mono); + base_real = ktime_add(tk->tkr_mono.base, + tk_core.timekeeper.offs_real); + base_raw = tk->tkr_raw.base; + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, + system_counterval.cycles); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, + system_counterval.cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); - timespec64_add_ns(ts_raw, nsecs_raw); - timespec64_add_ns(ts_real, nsecs_real); -} -EXPORT_SYMBOL(ktime_get_raw_and_real_ts64); + xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); + xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); -#endif /* CONFIG_NTP_PPS */ + /* + * Interpolate if necessary, adjusting back from the start of the + * current interval + */ + if (do_interp) { + cycle_t partial_history_cycles, total_history_cycles; + bool discontinuity; + + /* + * Check that the counter value occurs after the provided + * history reference and that the history doesn't cross a + * clocksource change + */ + if (!history_begin || + !cycle_between(history_begin->cycles, + system_counterval.cycles, cycles) || + history_begin->cs_was_changed_seq != cs_was_changed_seq) + return -EINVAL; + partial_history_cycles = cycles - system_counterval.cycles; + total_history_cycles = cycles - history_begin->cycles; + discontinuity = + history_begin->clock_was_set_seq != clock_was_set_seq; + + ret = adjust_historical_crosststamp(history_begin, + partial_history_cycles, + total_history_cycles, + discontinuity, xtstamp); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_gettimeofday - Returns the time of day in a timeval diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ab09829..05ddc08 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name) struct ftrace_event_field *field; struct list_head *head; - field = __find_event_field(&ftrace_generic_fields, name); + head = trace_get_fields(call); + field = __find_event_field(head, name); if (field) return field; - field = __find_event_field(&ftrace_common_fields, name); + field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; - head = trace_get_fields(call); - return __find_event_field(head, name); + return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, @@ -171,8 +171,10 @@ static int trace_define_generic_fields(void) { int ret; - __generic_field(int, cpu, FILTER_OTHER); - __generic_field(char *, comm, FILTER_PTR_STRING); + __generic_field(int, CPU, FILTER_CPU); + __generic_field(int, cpu, FILTER_CPU); + __generic_field(char *, COMM, FILTER_COMM); + __generic_field(char *, comm, FILTER_COMM); return ret; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f93a219..6816302 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps, return -EINVAL; } - if (is_string_field(field)) { + if (field->filter_type == FILTER_COMM) { + filter_build_regex(pred); + fn = filter_pred_comm; + pred->regex.field_len = TASK_COMM_LEN; + } else if (is_string_field(field)) { filter_build_regex(pred); - if (!strcmp(field->name, "comm")) { - fn = filter_pred_comm; - pred->regex.field_len = TASK_COMM_LEN; - } else if (field->filter_type == FILTER_STATIC_STRING) { + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) @@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps, } pred->val = val; - if (!strcmp(field->name, "cpu")) + if (field->filter_type == FILTER_CPU) fn = filter_pred_cpu; else fn = select_comparison_fn(pred->op, field->size, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c995644..21b81a4 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -30,7 +30,7 @@ struct trace_kprobe { struct list_head list; struct kretprobe rp; /* Use rp.kp for kprobe use */ - unsigned long nhit; + unsigned long __percpu *nhit; const char *symbol; /* symbol name */ struct trace_probe tp; }; @@ -274,6 +274,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, if (!tk) return ERR_PTR(ret); + tk->nhit = alloc_percpu(unsigned long); + if (!tk->nhit) + goto error; + if (symbol) { tk->symbol = kstrdup(symbol, GFP_KERNEL); if (!tk->symbol) @@ -313,6 +317,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, error: kfree(tk->tp.call.name); kfree(tk->symbol); + free_percpu(tk->nhit); kfree(tk); return ERR_PTR(ret); } @@ -327,6 +332,7 @@ static void free_trace_kprobe(struct trace_kprobe *tk) kfree(tk->tp.call.class->system); kfree(tk->tp.call.name); kfree(tk->symbol); + free_percpu(tk->nhit); kfree(tk); } @@ -874,9 +880,14 @@ static const struct file_operations kprobe_events_ops = { static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_kprobe *tk = v; + unsigned long nhit = 0; + int cpu; + + for_each_possible_cpu(cpu) + nhit += *per_cpu_ptr(tk->nhit, cpu); seq_printf(m, " %-44s %15lu %15lu\n", - trace_event_name(&tk->tp.call), tk->nhit, + trace_event_name(&tk->tp.call), nhit, tk->rp.kp.nmissed); return 0; @@ -1225,7 +1236,7 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); - tk->nhit++; + raw_cpu_inc(*tk->nhit); if (tk->tp.flags & TP_FLAG_TRACE) kprobe_trace_func(tk, regs); @@ -1242,7 +1253,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp); - tk->nhit++; + raw_cpu_inc(*tk->nhit); if (tk->tp.flags & TP_FLAG_TRACE) kretprobe_trace_func(tk, ri, regs); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 0655afb..d166308 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -186,11 +186,11 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, name) \ - sizeof(type) != sizeof(trace.name) ? \ +#define SYSCALL_FIELD(type, field, name) \ + sizeof(type) != sizeof(trace.field) ? \ __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), name), \ - sizeof(trace.name), is_signed_type(type) + #type, #name, offsetof(typeof(trace), field), \ + sizeof(trace.field), is_signed_type(type) static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -261,7 +261,8 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) int i; int offset = offsetof(typeof(trace), args); - ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), + FILTER_OTHER); if (ret) return ret; @@ -281,11 +282,12 @@ static int __init syscall_exit_define_fields(struct trace_event_call *call) struct syscall_trace_exit trace; int ret; - ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), + FILTER_OTHER); if (ret) return ret; - ret = trace_define_field(call, SYSCALL_FIELD(long, ret), + ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), FILTER_OTHER); return ret; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 975cb49..f8e26ab 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -93,9 +93,11 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) { struct mm_struct *mm; - /* convert pages-usec to Mbyte-usec */ - stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB; - stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB; + /* convert pages-nsec/1024 to Mbyte-usec, see __acct_update_integrals */ + stats->coremem = p->acct_rss_mem1 * PAGE_SIZE; + do_div(stats->coremem, 1000 * KB); + stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE; + do_div(stats->virtmem, 1000 * KB); mm = get_task_mm(p); if (mm) { /* adjust to KB unit */ @@ -123,27 +125,28 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) static void __acct_update_integrals(struct task_struct *tsk, cputime_t utime, cputime_t stime) { - if (likely(tsk->mm)) { - cputime_t time, dtime; - struct timeval value; - unsigned long flags; - u64 delta; - - local_irq_save(flags); - time = stime + utime; - dtime = time - tsk->acct_timexpd; - jiffies_to_timeval(cputime_to_jiffies(dtime), &value); - delta = value.tv_sec; - delta = delta * USEC_PER_SEC + value.tv_usec; - - if (delta == 0) - goto out; - tsk->acct_timexpd = time; - tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); - tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; - out: - local_irq_restore(flags); - } + cputime_t time, dtime; + u64 delta; + + if (!likely(tsk->mm)) + return; + + time = stime + utime; + dtime = time - tsk->acct_timexpd; + /* Avoid division: cputime_t is often in nanoseconds already. */ + delta = cputime_to_nsecs(dtime); + + if (delta < TICK_NSEC) + return; + + tsk->acct_timexpd = time; + /* + * Divide by 1024 to avoid overflow, and to avoid division. + * The final unit reported to userspace is Mbyte-usecs, + * the rest of the math is done in xacct_add_tsk. + */ + tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10; + tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10; } /** @@ -153,9 +156,12 @@ static void __acct_update_integrals(struct task_struct *tsk, void acct_update_integrals(struct task_struct *tsk) { cputime_t utime, stime; + unsigned long flags; + local_irq_save(flags); task_cputime(tsk, &utime, &stime); __acct_update_integrals(tsk, utime, stime); + local_irq_restore(flags); } /** |
